INDEX

Explanations

phrases indicating a strong argument or disagreement

oai_token-act-pair · gpt-3.5-turbo

instances of the word "argue" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Seym

-0.65

psy

-0.65

beam

-0.64

ecycle

-0.62

 Radiation

-0.60

mental

-0.60

fell

-0.60

-0.59

 Atomic

-0.59

cler

-0.57

POSITIVE LOGITS

 against

0.92

 convinc

0.89

 vehemently

0.89

 forcefully

0.85

 arguing

0.83

inet

0.83

 persu

0.82

uca

0.81

 passionately

0.81

 arguments

0.80

Activations Density 0.030%

phrases indicating a strong argument or disagreement

instances of the word "argue" and its variants

No Comments

No Known Activations