INDEX

Explanations

mentions of the adjective "mild" in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "mild" 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

berus

-0.73

andise

-0.69

 Blackwell

-0.68

alogue

-0.68

ynthesis

-0.68

ilater

-0.66

 Chase

-0.65

ÃįÃį

-0.65

 Dame

-0.64

 Framework

-0.64

POSITIVE LOGITS

er

1.18

est

1.10

ew

1.05

ers

0.98

erate

0.96

ener

0.92

ening

0.91

ering

0.86

ened

0.85

ens

0.81

Activations Density 0.014%

mentions of the adjective "mild" in various contexts

instances of the word "mild" and its variations

No Comments

No Known Activations