INDEX

Explanations

social media metrics and affiliations with organizations

oai_token-act-pair · gpt-3.5-turbo

references to social media 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

WARD

-0.85

advertising

-0.85

Ĥİ

-0.77

 Cosponsors

-0.75

ãĤ¹ãĥĪ

-0.73

jen

-0.70

ulp

-0.69

Sport

-0.67

GEN

-0.65

HAEL

-0.64

POSITIVE LOGITS

 knack

0.94

 lined

0.86

 capability

0.82

 spare

0.75

 flair

0.75

 overlap

0.73

 installed

0.73

 chance

0.72

 figured

0.72

 fetish

0.71

Activations Density 0.897%

social media metrics and affiliations with organizations

references to social media metrics

No Comments

No Known Activations