INDEX

Explanations

mentions or references to approvals or agreements

oai_token-act-pair · gpt-3.5-turbo

references to various forms of approval in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

hed

-0.83

gm

-0.71

grave

-0.70

tern

-0.70

Alz

-0.68

Corn

-0.66

tal

-0.66

lla

-0.66

Cop

-0.65

ulative

-0.64

POSITIVE LOGITS

 approval

1.19

 approvals

1.18

 ratings

1.02

 rating

0.98

 clearance

0.95

 approves

0.95

 commissions

0.92

orship

0.91

 approve

0.87

worthy

0.86

Activations Density 0.017%

mentions or references to approvals or agreements

references to various forms of approval in different contexts

No Comments

No Known Activations