INDEX

Explanations

phrases referring to something specific or highlighting a particular aspect

oai_token-act-pair · gpt-3.5-turbo

instances of the word "this."

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

ãĤ¹ãĥĪ

-0.88

omo

-0.81

amia

-0.72

©¶æ¥µ

-0.70

 è£ıè¦ļéĨĴ

-0.70

raq

-0.69

ickets

-0.68

Ñĥ

-0.68

pots

-0.66

ãĥı

-0.66

POSITIVE LOGITS

 week

0.95

 trope

0.93

guy

0.83

 incarnation

0.81

 year

0.79

 month

0.79

 installment

0.78

 WEEK

0.78

 weekend

0.77

 latest

0.77

Activations Density 0.226%

phrases referring to something specific or highlighting a particular aspect

instances of the word "this."

No Comments

No Known Activations