INDEX

Explanations

instances of the word "family" and its variations or related contexts

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

mentions of family or family-related terms

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/(

-0.74

inen

-0.69

argon

-0.69

ovi

-0.69

 hypoc

-0.67

ane

-0.66

 Subtle

-0.65

psey

-0.65

eous

-0.64

 Archdemon

-0.63

POSITIVE LOGITS

ilial

0.96

ILY

0.96

hood

0.96

 resemb

0.96

 reunion

0.94

members

0.91

 members

0.87

 resemblance

0.86

 caregivers

0.86

 reun

0.85

Activations Density 0.047%

instances of the word "family" and its variations or related contexts

mentions of family or family-related terms

No Comments

No Known Activations