INDEX

Explanations

words related to urgent or extreme situations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "desperate" indicating urgent or dire situations

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

roma

-0.82

rust

-0.77

ership

-0.74

rats

-0.73

icipated

-0.72

Ģ

-0.71

nesota

-0.71

agree

-0.70

inion

-0.70

ificantly

-0.69

POSITIVE LOGITS

 pleas

0.81

 conflic

0.75

 plea

0.75

 desperate

0.73

 pleading

0.73

 desperation

0.72

 situations

0.72

 Measures

0.72

 desperately

0.72

 migrants

0.69

Activations Density 0.032%

words related to urgent or extreme situations

instances of the word "desperate" indicating urgent or dire situations

No Comments

No Known Activations