INDEX

Explanations

mentions of someone or something making a return

oai_token-act-pair · gpt-3.5-turbo

mentions of returns, particularly in contexts related to media, entertainment, or sports

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

iop

-0.75

vern

-0.73

ahi

-0.69

Administ

-0.67

ihad

-0.65

å¤©

-0.64

\\\\\\\\

-0.64

Corp

-0.63

rpm

-0.63

urity

-0.62

POSITIVE LOGITS

ees

1.00

 home

0.80

 HOME

0.70

owship

0.70

home

0.68

ends

0.67

wcs

0.64

 haunt

0.62

roads

0.61

 unsc

0.61

Activations Density 0.026%

mentions of someone or something making a return

mentions of returns, particularly in contexts related to media, entertainment, or sports

No Comments

No Known Activations