INDEX

Explanations

mentions of specific names or terms "Ab" and its variations with related numbers

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names or locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pher

-0.58

 Compass

-0.56

gerald

-0.55

 Norton

-0.55

patrick

-0.55

glers

-0.54

 dogs

-0.54

 companion

-0.51

 manufact

-0.51

 kittens

-0.51

POSITIVE LOGITS

zeb

0.81

aze

0.72

ande

0.71

oga

0.70

ollah

0.69

abi

0.68

NAS

0.68

oya

0.67

asy

0.66

ichi

0.66

Activations Density 0.165%

mentions of specific names or terms "Ab" and its variations with related numbers

mentions of specific names or locations

No Comments

No Known Activations