INDEX

Explanations

mentions of physical and mental health-related terms and situations

oai_token-act-pair · gpt-3.5-turbo

the presence of negative constructions related to ability or capability

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

 Zeit

-0.61

 theaters

-0.57

 lump

-0.56

Ruk

-0.55

 chunks

-0.55

 doomed

-0.54

 LINE

-0.54

 town

-0.54

 nominations

-0.54

 skewed

-0.53

POSITIVE LOGITS

pload

0.91

ivably

0.80

urry

0.77

tem

0.77

reason

0.77

ħĭ

0.76

apply

0.74

submit

0.74

ı

0.72

¶ħ

0.71

Activations Density 0.117%

mentions of physical and mental health-related terms and situations

the presence of negative constructions related to ability or capability

No Comments

No Known Activations