INDEX

Explanations

words related to accessing information or data

oai_token-act-pair · gpt-3.5-turbo

instances of the word "access" 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

stal

-0.63

balls

-0.62

 coat

-0.62

hair

-0.60

warm

-0.59

break

-0.59

 abst

-0.59

ector

-0.58

thin

-0.58

ignore

-0.58

POSITIVE LOGITS

ibly

1.20

ibility

1.18

ible

0.91

IBLE

0.90

ioned

0.86

prises

0.85

ITNESS

0.83

ibl

0.80

ibles

0.80

eport

0.78

Activations Density 0.025%

words related to accessing information or data

instances of the word "access" and its variations

No Comments

No Known Activations