INDEX

Explanations

words related to political or organizational policies

oai_token-act-pair · gpt-3.5-turbo

references to government policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

thouse

-0.80

rez

-0.80

 Sabha

-0.74

semble

-0.69

naissance

-0.65

Ort

-0.64

 sensation

-0.64

iever

-0.64

zzi

-0.64

Ou

-0.62

POSITIVE LOGITS

 policies

3.63

 Policies

2.95

 policy

2.40

policy

2.05

 Policy

1.92

Policy

1.92

 laws

1.61

 stances

1.61

 initiatives

1.53

 strategies

1.53

Activations Density 0.015%

words related to political or organizational policies

references to government policies

No Comments

No Known Activations