INDEX

Explanations

percentages and growth rates

oai_token-act-pair · gpt-3.5-turbo

phrases related to statistical increases or growth metrics

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

 staples

-0.62

english

-0.62

å¤©

-0.61

PAR

-0.60

ographies

-0.59

 Nichols

-0.57

 mant

-0.57

 Names

-0.56

 Cabin

-0.56

dies

-0.56

POSITIVE LOGITS

xual

1.11

over

0.85

 rate

0.76

ait

0.76

jriwal

0.76

ahead

0.76

emaker

0.76

onential

0.75

 subsequ

0.74

alore

0.74

Activations Density 0.098%

percentages and growth rates

phrases related to statistical increases or growth metrics

No Comments

No Known Activations