INDEX

Explanations

instances of the word "authority"

oai_token-act-pair · gpt-3.5-turbo

references to authority figures or concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Lens

-0.74

 Shal

-0.70

 Lovely

-0.68

auder

-0.68

irling

-0.68

pocket

-0.68

neys

-0.67

lla

-0.66

eful

-0.66

esta

-0.64

POSITIVE LOGITS

 authority

1.00

 delegated

0.98

 vested

0.97

Reviewer

0.91

 exercised

0.85

 figures

0.85

 conferred

0.84

 overseeing

0.78

 nomine

0.78

 confir

0.77

Activations Density 0.028%

instances of the word "authority"

references to authority figures or concepts

No Comments

No Known Activations