INDEX

Explanations

words related to opinions or statements of expression

oai_token-act-pair · gpt-3.5-turbo

instances of the word "expressed."

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

etheless

-0.68

idd

-0.68

Peb

-0.66

 Levi

-0.64

strap

-0.63

pping

-0.62

pped

-0.62

 Skydragon

-0.62

behind

-0.62

jack

-0.62

POSITIVE LOGITS

 doubts

0.98

 condolences

0.90

 displeasure

0.90

 frustrations

0.83

 gratitude

0.80

 frustration

0.80

 fears

0.79

uron

0.79

 vows

0.79

 dissatisfaction

0.78

Activations Density 0.020%

words related to opinions or statements of expression

instances of the word "expressed."

No Comments

No Known Activations