INDEX

Explanations

specific nouns related to information or subjects of discussion

oai_token-act-pair · gpt-3.5-turbo

nouns or terms related to objects, events, or concepts that signify important elements within a document

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hovah

-0.60

anwhile

-0.53

layer

-0.52

ofi

-0.52

conservancy

-0.50

 Lover

-0.49

 Fortune

-0.48

uilt

-0.47

 Canaveral

-0.47

joice

-0.47

POSITIVE LOGITS

 lightly

0.59

natureconservancy

0.59

 herein

0.58

 methodology

0.53

METHOD

0.52

Abstract

0.51

Applic

0.51

enge

0.50

 GOODMAN

0.50

 imply

0.49

Activations Density 1.142%

specific nouns related to information or subjects of discussion

nouns or terms related to objects, events, or concepts that signify important elements within a document

No Comments

No Known Activations