INDEX

Explanations

phrases related to stopping or preventing actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "stop" and related phrases emphasizing cessation or interruption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

eton

-0.73

icol

-0.72

é¾įåĸļå£«

-0.68

æĪ¦

-0.68

çīĪ

-0.66

igree

-0.64

soDeliveryDate

-0.64

ittal

-0.64

 deserts

-0.61

lot

-0.61

POSITIVE LOGITS

 bleeding

0.97

ãĤ®

0.79

 movement

0.74

 cheating

0.72

 execution

0.71

smoking

0.71

 lockout

0.70

angering

0.70

 breathing

0.68

 bothering

0.68

Activations Density 0.132%

phrases related to stopping or preventing actions

instances of the word "stop" and related phrases emphasizing cessation or interruption

No Comments

No Known Activations