INDEX

Explanations

phrases related to something being the basis or inspiration for something else

oai_token-act-pair · gpt-3.5-turbo

the term "based" in relation to various contexts or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

antha

-0.75

dra

-0.73

ESE

-0.71

apes

-0.70

å¥³

-0.66

shr

-0.66

ãģı

-0.65

ests

-0.63

osen

-0.63

ese

-0.62

POSITIVE LOGITS

 loosely

0.89

 upon

0.79

 solely

0.79

awaru

0.74

ragon

0.68

 withd

0.68

illac

0.68

 certific

0.68

amera

0.67

lly

0.66

Activations Density 0.022%

phrases related to something being the basis or inspiration for something else

the term "based" in relation to various contexts or narratives

No Comments

No Known Activations