INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

references to numerical quantities or groups

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

ifice

-0.86

 guiActiveUnfocused

-0.79

oper

-0.71

Ïī

-0.69

opia

-0.69

ocracy

-0.68

drive

-0.68

activity

-0.66

omo

-0.64

senal

-0.63

POSITIVE LOGITS

teen

1.39

een

1.08

 Ways

0.97

 Months

0.96

 Weeks

0.91

Thirty

0.91

 hundred

0.89

 weeks

0.88

 Hours

0.87

 months

0.87

Activations Density 0.141%

proper nouns

references to numerical quantities or groups

No Comments

No Known Activations