INDEX

Explanations

the word "substitute"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "substitute" and its variations

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

stra

-0.76

worthiness

-0.74

erer

-0.74

erers

-0.74

bra

-0.72

trust

-0.72

Bird

-0.70

raq

-0.70

 Decay

-0.65

bear

-0.65

POSITIVE LOGITS

itute

1.09

utions

1.02

 substit

0.88

 substitutes

0.86

 substitute

0.85

itutes

0.79

uting

0.79

 Subst

0.78

 substituted

0.76

aneous

0.75

Activations Density 0.020%

the word "substitute"

occurrences of the word "substitute" and its variations

No Comments

No Known Activations