INDEX

Explanations

phrases related to introducing information or sharing findings

oai_token-act-pair · gpt-3.5-turbo

mentions of introductory phrases or transitioning statements

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

 Used

-0.68

['

-0.64

ilage

-0.63

 externalToEVAOnly

-0.62

å£«

-0.62

Charges

-0.61

 msec

-0.61

lycer

-0.60

irgin

-0.60

 distance

-0.59

POSITIVE LOGITS

 curated

0.87

 infographic

0.81

 VICE

0.77

 HuffPost

0.73

 pals

0.73

sonian

0.72

 dive

0.71

 Geek

0.69

 retrospective

0.66

 rundown

0.66

Activations Density 0.671%

phrases related to introducing information or sharing findings

mentions of introductory phrases or transitioning statements

No Comments

No Known Activations