INDEX

Explanations

text related to historical information or editing content

oai_token-act-pair · gpt-3.5-turbo

elements related to formatting or editing in a document

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

andel

-0.81

uters

-0.79

emouth

-0.78

uple

-0.77

ueless

-0.76

onds

-0.73

krit

-0.71

umbers

-0.71

milo

-0.69

undle

-0.69

POSITIVE LOGITS

 Origins

0.81

Background

0.74

ãĤ¨ãĥ«

0.74

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.72

 Soviets

0.71

Appearance

0.71

 adaptations

0.71

Appearances

0.69

 origins

0.69

Production

0.69

Activations Density 0.068%

text related to historical information or editing content

elements related to formatting or editing in a document

No Comments

No Known Activations