INDEX

Explanations

statements indicating holding law enforcement accountable

oai_token-act-pair · gpt-3.5-turbo

instances of formal or administrative mentions related to organizations or institutions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

foc

-0.87

 altern

-0.81

 favour

-0.80

 stabil

-0.77

 encomp

-0.76

 aggreg

-0.75

 excluded

-0.73

 oscill

-0.73

 ranged

-0.73

 regener

-0.73

POSITIVE LOGITS

WASHINGTON

1.79

SAN

1.62

LOS

1.61

Updated

1.60

TOR

1.53

NEW

1.50

PORT

1.48

Published

1.46

SHARE

1.43

By

1.41

Activations Density 0.293%

statements indicating holding law enforcement accountable

instances of formal or administrative mentions related to organizations or institutions

No Comments

No Known Activations