INDEX

Explanations

capitalized words that appear to be names or titles

oai_token-act-pair · gpt-3.5-turbo

names of organizations and notable individuals in various contexts

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

anova

-0.81

icipated

-0.69

idays

-0.66

incial

-0.66

accompan

-0.65

twitter

-0.64

comings

-0.63

oola

-0.62

udeau

-0.62

Reviewed

-0.61

POSITIVE LOGITS

ploy

0.75

 Wonderland

0.72

 Fortune

0.72

 coli

0.71

 Lauder

0.69

iencies

0.68

 Gutierrez

0.65

 Faust

0.64

Sah

0.62

hower

0.62

Activations Density 0.386%

capitalized words that appear to be names or titles

names of organizations and notable individuals in various contexts

No Comments

No Known Activations