INDEX

Explanations

phrases related to political figures and events

oai_token-act-pair · gpt-3.5-turbo

mentions of specific organizations, news agencies, or entities related to media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

osponsors

-0.72

taboola

-0.70

 differe

-0.63

abor

-0.62

ordinate

-0.60

abet

-0.59

 cumbers

-0.59

itÃ©

-0.59

ospons

-0.58

 anat

-0.58

POSITIVE LOGITS

1.02

1.01

1.00

0.99

0.98

0.97

0.96

Activations Density 0.044%

phrases related to political figures and events

mentions of specific organizations, news agencies, or entities related to media

No Comments

No Known Activations