INDEX

Explanations

explanations or descriptions of events or situations

oai_token-act-pair · gpt-3.5-turbo

phrases and words related to providing explanations

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

ymph

-0.79

illet

-0.78

ibaba

-0.78

estial

-0.75

yss

-0.72

oned

-0.72

inion

-0.72

sembly

-0.69

opers

-0.69

yard

-0.69

POSITIVE LOGITS

WHY

0.98

why

0.86

 explanations

0.86

 explanation

0.85

 thereof

0.84

ãĤ©

0.79

why

0.76

xual

0.76

Origin

0.75

aries

0.74

Activations Density 0.020%

explanations or descriptions of events or situations

phrases and words related to providing explanations

No Comments

No Known Activations