INDEX

Explanations

abbreviations and titles with periods

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

enegger

-0.66

jah

-0.64

 Mara

-0.61

 biome

-0.59

oxide

-0.56

azeera

-0.55

picture

-0.54

ãĥķ

-0.54

ãĤ´ãĥ³

-0.54

 emanc

-0.54

POSITIVE LOGITS

ongyang

0.92

 Lovecraft

0.80

ople

0.76

ĵĺ

0.73

sylvania

0.67

ivot

0.66

ERSON

0.66

terson

0.65

cipled

0.64

orters

0.63

Activations Density 0.043%

abbreviations and titles with periods

punctuation marks, specifically periods

No Comments

No Known Activations