INDEX

Explanations

words related to editing in various contexts

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

phal

-0.83

 opio

-0.78

ptoms

-0.75

hood

-0.74

fall

-0.73

fal

-0.70

gins

-0.69

falls

-0.69

ãĤ©

-0.67

fund

-0.66

POSITIVE LOGITS

 editing

0.86

orship

0.86

 edits

0.79

ettings

0.79

 summ

0.79

ipedia

0.72

 Delete

0.71

ovie

0.70

 commons

0.70

 delete

0.70

Activations Density 0.033%

words related to editing in various contexts

No Comments

No Known Activations