INDEX

Explanations

actions related to decision making or cancellation

oai_token-act-pair · gpt-3.5-turbo

words associated with legislative actions regarding approvals and denials

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ingham

-0.75

agent

-0.74

izes

-0.72

abet

-0.72

ivities

-0.71

eners

-0.71

alter

-0.70

strength

-0.68

itis

-0.68

arist

-0.68

POSITIVE LOGITS

uled

0.94

 aback

0.89

ĸļ

0.87

CLASSIFIED

0.85

 unanimously

0.80

©¶æ¥µ

0.77

ocument

0.76

 exting

0.75

nesday

0.73

DeliveryDate

0.71

Activations Density 0.075%

actions related to decision making or cancellation

words associated with legislative actions regarding approvals and denials

No Known Activations