INDEX

Explanations

mentions of different communities or industries

oai_token-act-pair · gpt-3.5-turbo

references to various communities and industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tein

-0.77

 confir

-0.67

eness

-0.66

å§«

-0.66

irin

-0.66

reditary

-0.65

gencies

-0.65

edIn

-0.64

peed

-0.63

ļé

-0.61

POSITIVE LOGITS

 itself

1.14

places

0.86

waves

0.82

 writ

0.77

osphere

0.77

 continuum

0.76

soDeliveryDate

0.75

ament

0.75

 revolving

0.71

 overseen

0.71

Activations Density 0.281%

mentions of different communities or industries

references to various communities and industries

No Comments

No Known Activations