INDEX

Explanations

words related to government and government actions

oai_token-act-pair · gpt-3.5-turbo

mentions of government

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

linger

-0.86

thora

-0.77

ostic

-0.76

issan

-0.75

ossibility

-0.73

alos

-0.73

ener

-0.70

lihood

-0.69

Gamer

-0.69

upper

-0.69

POSITIVE LOGITS

 officials

1.24

 agencies

1.16

 offices

1.03

 employees

1.01

 coffers

1.01

 bureaucrats

0.98

 institutions

0.98

 bureaucr

0.98

 official

0.95

 administrators

0.95

Activations Density 0.205%

words related to government and government actions

mentions of government

No Comments

No Known Activations