INDEX

Explanations

statistical data mentioned in text

oai_token-act-pair · gpt-3.5-turbo

references to statistical data and reports

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

uran

-0.85

por

-0.76

aline

-0.73

gur

-0.72

ergy

-0.71

rin

-0.71

ModLoader

-0.69

lain

-0.68

Interstitial

-0.68

sole

-0.68

POSITIVE LOGITS

Statistics

0.84

ãĤ¼ãĤ¦ãĤ¹

0.82

 Bunny

0.76

 statistics

0.74

iologist

0.74

istics

0.73

iological

0.69

iology

0.69

Reporting

0.66

 compiled

0.66

Activations Density 0.031%

statistical data mentioned in text

references to statistical data and reports

No Comments

No Known Activations