INDEX

Explanations

keywords related to authorizations, licenses, and specific entities

oai_token-act-pair · gpt-3.5-turbo

sequences of letters or abbreviations, particularly those that appear in online contexts

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

 Takeru

-0.70

ktop

-0.70

bender

-0.63

 afore

-0.59

 equipped

-0.58

 lest

-0.58

 knots

-0.57

swick

-0.57

 envy

-0.56

 quake

-0.56

POSITIVE LOGITS

unte

0.87

bilt

0.87

illa

0.80

imir

0.78

ado

0.78

uel

0.78

emort

0.78

iman

0.78

¶æ

0.76

ili

0.76

Activations Density 0.110%

keywords related to authorizations, licenses, and specific entities

sequences of letters or abbreviations, particularly those that appear in online contexts

No Comments

No Known Activations