INDEX

Explanations

keywords related to equipment features or technical specifications

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "up," including variations in capitalization

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

 Niet

-0.71

gee

-0.64

 Canaver

-0.64

 deleg

-0.63

 Kahn

-0.61

tein

-0.61

 Beir

-0.60

#$

-0.60

 Canary

-0.59

 Mori

-0.57

POSITIVE LOGITS

river

0.85

stairs

0.85

np

0.80

dates

0.78

][

0.77

cakes

0.76

grades

0.75

wind

0.73

votes

0.72

skirts

0.71

Activations Density 0.016%

keywords related to equipment features or technical specifications

occurrences of the word "up," including variations in capitalization

No Comments

No Known Activations