INDEX

Explanations

questions about the truth or nature of statements made

oai_token-act-pair · gpt-3.5-turbo

questions that challenge assumptions or beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

bies

-0.90

dit

-0.79

usters

-0.77

tions

-0.73

papers

-0.71

Topics

-0.71

umbn

-0.69

ixels

-0.69

ventures

-0.68

former

-0.67

POSITIVE LOGITS

 conceivable

1.02

 really

0.95

 worth

0.91

 possible

0.89

 Possible

0.88

 ever

0.87

 Really

0.85

 worthwhile

0.83

 feasible

0.83

 REALLY

0.83

Activations Density 0.057%

questions about the truth or nature of statements made

questions that challenge assumptions or beliefs

No Comments

No Known Activations