INDEX

Explanations

words related to governance and control

oai_token-act-pair · gpt-3.5-turbo

references to different forms of governance or authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ãĥ¤

-0.72

 lymph

-0.71

 reviewer

-0.67

velength

-0.65

£ı

-0.65

 Brees

-0.64

TOM

-0.63

izon

-0.63

Sensor

-0.63

DERR

-0.61

POSITIVE LOGITS

pin

0.83

rule

0.74

unta

0.74

govern

0.73

ocratic

0.72

doms

0.71

puff

0.71

orship

0.70

ocracy

0.70

 Policies

0.70

Activations Density 0.038%

words related to governance and control

references to different forms of governance or authority

No Comments

No Known Activations