INDEX

Explanations

mentions of organizations or campaigns

oai_token-act-pair · gpt-3.5-turbo

mentions of organizations, notable individuals, and institutions related to social issues and legal contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

frame

-0.90

fram

-0.84

rome

-0.84

station

-0.82

wagen

-0.80

stay

-0.80

frames

-0.79

hab

-0.79

uten

-0.78

train

-0.77

POSITIVE LOGITS

 NAACP

1.00

 GOODMAN

0.84

ONSORED

0.82

 Cosponsors

0.78

 glim

0.78

ICS

0.77

ENTS

0.76

 Legal

0.74

ACP

0.73

resents

0.73

Activations Density 0.026%

mentions of organizations or campaigns

mentions of organizations, notable individuals, and institutions related to social issues and legal contexts

No Comments

No Known Activations