INDEX

Explanations

phrases or words related to communication, introductions, and transitions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating repetition or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

cli

-0.76

ascript

-0.74

quartered

-0.67

RNA

-0.67

cale

-0.66

DNA

-0.66

Enhanced

-0.64

ajor

-0.64

pend

-0.63

dating

-0.63

POSITIVE LOGITS

 importantly

0.82

 therein

0.80

cru

0.78

 secondly

0.75

 prest

0.72

 lest

0.71

 kicker

0.70

vo

0.70

 concludes

0.70

 finally

0.69

Activations Density 0.225%

phrases or words related to communication, introductions, and transitions

phrases indicating repetition or emphasis

No Comments

No Known Activations