INDEX

Explanations

questions about the effectiveness or impact of certain actions or decisions

oai_token-act-pair · gpt-3.5-turbo

questions about political concepts and news headlines

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aples

-0.78

awa

-0.73

 seiz

-0.73

rul

-0.70

ifax

-0.69

 stroke

-0.69

 hiber

-0.67

 brush

-0.67

 foreground

-0.66

 looph

-0.66

POSITIVE LOGITS

 Productions

0.98

!,

0.91

 Strategies

0.88

Ltd

0.82

Leaks

0.82

Sport

0.82

 Collective

0.81

0.80

 Voices

0.79

 Films

0.79

Activations Density 0.490%

questions about the effectiveness or impact of certain actions or decisions

questions about political concepts and news headlines

No Comments

No Known Activations