INDEX

Explanations

phrases related to actions or decisions, often involving political figures or public statements

oai_token-act-pair · gpt-3.5-turbo

statements about political actions or decisions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 unison

-0.63

 âĶľâĶĢâĶĢ

-0.63

selves

-0.59

taboola

-0.54

mination

-0.54

 backgrounds

-0.53

 Grid

-0.52

 Container

-0.52

 collective

-0.52

 combined

-0.51

POSITIVE LOGITS

 himself

1.14

 Himself

0.88

 assassinated

0.75

 veto

0.73

 personally

0.67

his

0.65

ardless

0.59

farious

0.58

 herself

0.57

 reelection

0.56

Activations Density 0.985%

phrases related to actions or decisions, often involving political figures or public statements

statements about political actions or decisions

No Comments

No Known Activations