INDEX

Explanations

copyright and usage terms

oai_token-act-pair · gpt-3.5-turbo

terms related to content usage rights and licensing agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 caution

-0.75

wake

-0.68

 preced

-0.66

 scapego

-0.66

 Galile

-0.62

 largeDownload

-0.62

naire

-0.60

eering

-0.60

 Mock

-0.59

 Hann

-0.59

POSITIVE LOGITS

Digital

0.71

Domain

0.68

lishes

0.66

east

0.65

Asset

0.64

 Domain

0.61

ibrarian

0.60

Republic

0.59

Ed

0.59

utenberg

0.59

Activations Density 0.040%

copyright and usage terms

terms related to content usage rights and licensing agreements

No Comments

No Known Activations