INDEX

Explanations

mentions of legal actions, specifically relating to political figures and the process of impeachment

oai_token-act-pair · gpt-3.5-turbo

references to impeachment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

othe

-0.75

nown

-0.72

WAR

-0.70

CAP

-0.69

VIS

-0.69

istic

-0.69

Metro

-0.69

IGH

-0.69

OWN

-0.68

variable

-0.66

POSITIVE LOGITS

 impeachment

1.41

 impe

1.21

 proceedings

0.82

agate

0.80

 indicted

0.76

urated

0.76

inating

0.75

 hearings

0.75

cano

0.73

 overth

0.72

Activations Density 0.010%

mentions of legal actions, specifically relating to political figures and the process of impeachment

references to impeachment

No Comments

No Known Activations