INDEX

Explanations

mentions of government officials and legal terms

oai_token-act-pair · gpt-3.5-turbo

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

acters

-0.79

ters

-0.70

points

-0.67

pots

-0.65

hered

-0.64

nown

-0.64

Sea

-0.64

ãĥ¼ãĤ¯

-0.64

âķĲ

-0.63

Prev

-0.63

POSITIVE LOGITS

 Eric

0.75

 Sessions

0.74

 Counsel

0.72

Pam

0.71

 prosecutor

0.71

 Amnesty

0.69

 Mattis

0.69

Kam

0.69

istration

0.69

 Lore

0.69

Activations Density 0.032%

mentions of government officials and legal terms

No Comments

No Known Activations