INDEX

Explanations

phrases indicating logical or justifiable explanations or causes

oai_token-act-pair · gpt-3.5-turbo

phrases indicating justification or rationale

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

semble

-0.83

chin

-0.77

 Carbuncle

-0.70

oba

-0.70

 Ping

-0.64

ega

-0.63

 Territories

-0.62

rongh

-0.61

inav

-0.61

eg

-0.61

POSITIVE LOGITS

why

0.92

 justifying

0.91

 whatsoever

0.85

pointers

0.84

Reviewer

0.81

abl

0.76

 justify

0.74

 justification

0.73

forward

0.73

WHY

0.72

Activations Density 0.026%

phrases indicating logical or justifiable explanations or causes

phrases indicating justification or rationale

No Comments

No Known Activations