INDEX

Explanations

names or terms related to political figures or leaders

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly political figures

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 catapult

-0.68

OPLE

-0.64

lamm

-0.60

 horm

-0.60

 mast

-0.59

 rake

-0.59

 context

-0.59

wcsstore

-0.58

 Roundup

-0.58

osterone

-0.58

POSITIVE LOGITS

vu

0.89

issance

0.78

heed

0.75

ongo

0.73

warm

0.73

zee

0.72

emort

0.71

eur

0.71

inho

0.71

anamo

0.70

Activations Density 0.219%

names or terms related to political figures or leaders

references to specific individuals, particularly political figures

No Comments

No Known Activations