INDEX

Explanations

years from the year 2014 mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

references to the year 2014

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ishing

-0.95

ishes

-0.81

isher

-0.75

ishment

-0.73

ISH

-0.73

ype

-0.72

abilia

-0.72

itionally

-0.71

ishers

-0.70

atio

-0.68

POSITIVE LOGITS

å¹

0.96

 onwards

0.81

0.71

assetsadobe

0.71

etheus

0.69

âĢ³

0.68

âĢ²

0.66

 Sochi

0.65

âĹ¼

0.65

onomy

0.64

Activations Density 0.043%

years from the year 2014 mentioned in the text

references to the year 2014

No Comments

No Known Activations