INDEX

Explanations

phrases indicating a condition to be met or an action to be taken regardless of personal feelings or circumstances

oai_token-act-pair · gpt-3.5-turbo

conditional statements or phrases indicating hypothetical scenarios

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

Ack

-0.72

reen

-0.62

 Argon

-0.61

Ell

-0.59

Gam

-0.58

Kut

-0.58

Reply

-0.57

 Shel

-0.57

 Berk

-0.57

 Cout

-0.57

POSITIVE LOGITS

 technically

0.85

 concede

0.82

 slight

0.79

 occasional

0.77

 ostensibly

0.77

 slightest

0.73

ometimes

0.72

 disagree

0.71

 SOME

0.70

 concedes

0.68

Activations Density 0.178%

phrases indicating a condition to be met or an action to be taken regardless of personal feelings or circumstances

conditional statements or phrases indicating hypothetical scenarios

No Comments

No Known Activations