INDEX

Explanations

phrases indicating fear or lack of fear in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of fear or anxiety-related terms

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

issance

-0.80

cise

-0.76

byter

-0.69

akeru

-0.69

eret

-0.67

erry

-0.66

anmar

-0.66

ankind

-0.65

eor

-0.65

dates

-0.65

POSITIVE LOGITS

 lest

1.16

 afraid

0.87

of

0.79

NESS

0.74

ptin

0.72

lessly

0.72

onda

0.71

 thereof

0.71

mong

0.71

crow

0.70

Activations Density 0.031%

phrases indicating fear or lack of fear in various contexts

instances of fear or anxiety-related terms

No Comments

No Known Activations