INDEX

Explanations

names of companies

oai_token-act-pair · gpt-3.5-turbo

references to various companies

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

 guiActiveUn

-0.83

icted

-0.73

acious

-0.73

iscopal

-0.72

dos

-0.71

*/(

-0.71

ividual

-0.71

 thorn

-0.69

 Nadu

-0.68

uckland

-0.68

POSITIVE LOGITS

Ltd

0.86

wide

0.80

ptives

0.79

LTD

0.75

 headquartered

0.74

 Limited

0.73

 Company

0.72

mens

0.71

 Fathers

0.69

 Holding

0.69

Activations Density 0.020%

names of companies

references to various companies

No Comments

No Known Activations