INDEX

Explanations

punctuation marks

oai_token-act-pair · gpt-3.5-turbo

enumerated list items or points made in a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

alian

-0.71

edi

-0.70

izz

-0.69

bern

-0.68

yle

-0.66

ulla

-0.66

 grocer

-0.65

buck

-0.63

sta

-0.63

 dictionary

-0.60

POSITIVE LOGITS

ãĤ´ãĥ³

0.76

————————

0.71

 Syndicate

0.68

[+

0.68

————————————————

0.67

————

0.66

 Quit

0.65

 Prot

0.65

 Prol

0.63

 Releases

0.63

Activations Density 0.019%

punctuation marks

enumerated list items or points made in a discussion

No Comments

No Known Activations