INDEX

Explanations

questions about identity, responsibility, and authority

oai_token-act-pair · gpt-3.5-turbo

references to questioned identities and roles

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

 Locations

-0.74

framework

-0.74

iation

-0.68

nothing

-0.67

ranging

-0.66

irth

-0.66

inery

-0.66

ossibility

-0.65

requ

-0.65

avascript

-0.65

POSITIVE LOGITS

 whom

0.98

 responsible

0.83

 footing

0.80

 accountable

0.79

 wiser

0.75

?]

0.75

who

0.75

 benef

0.73

 cheated

0.72

cyn

0.71

Activations Density 0.119%

questions about identity, responsibility, and authority

references to questioned identities and roles

No Comments

No Known Activations