INDEX

Explanations

references to cookies, specifically focusing on actions involving cookies like making, eating, and tracking them

oai_token-act-pair · gpt-3.5-turbo

references to cookies, both as a food item and in a metaphorical context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SI

-0.71

ashtra

-0.70

ities

-0.68

rior

-0.64

abouts

-0.63

orth

-0.63

WAYS

-0.62

ity

-0.62

ORN

-0.62

itate

-0.62

POSITIVE LOGITS

 cookies

1.24

 dough

1.09

 Clicker

1.09

 cookie

1.07

jar

1.01

 Cookies

1.00

 Cookie

0.97

cookie

0.96

 cutter

0.95

 jars

0.92

Activations Density 0.015%

references to cookies, specifically focusing on actions involving cookies like making, eating, and tracking them

references to cookies, both as a food item and in a metaphorical context

No Comments

No Known Activations