INDEX

Explanations

words related to positive opinions or conditions

oai_token-act-pair · gpt-3.5-turbo

words associated with positive evaluations and favorable conditions

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

agos

-0.84

hod

-0.79

ngth

-0.78

prototype

-0.78

lang

-0.76

lua

-0.76

bus

-0.76

hid

-0.75

grave

-0.74

rum

-0.74

POSITIVE LOGITS

 matchups

1.11

 favorable

1.08

 favourable

0.97

avorable

0.96

 conditions

0.89

 margins

0.87

 unfavorable

0.86

 matchup

0.85

 agre

0.85

 arrangement

0.82

Activations Density 0.022%

words related to positive opinions or conditions

words associated with positive evaluations and favorable conditions

No Comments

No Known Activations