INDEX

Explanations

proper nouns related to different people and places

oai_token-act-pair · gpt-3.5-turbo

words related to organizational roles or actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itself

-0.67

Xer

-0.63

imgur

-0.62

=/

-0.59

una

-0.56

itiz

-0.55

 relies

-0.55

 lasts

-0.54

 doesnt

-0.54

fav

-0.53

POSITIVE LOGITS

 respectively

1.76

 respective

1.26

 apiece

1.18

 jointly

1.10

 collectively

0.97

 together

0.96

 Together

0.87

together

0.86

 themselves

0.84

selves

0.83

Activations Density 1.089%

proper nouns related to different people and places

words related to organizational roles or actions

No Comments

No Known Activations