INDEX

Explanations

answers or responses within a sentence

oai_token-act-pair · gpt-3.5-turbo

assertions or statements that present information or answers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ership

-0.76

rongh

-0.68

ombat

-0.68

idi

-0.66

 Cutting

-0.66

 Defenders

-0.64

roying

-0.63

ivities

-0.62

Keefe

-0.62

 Samar

-0.62

POSITIVE LOGITS

YES

0.99

yes

0.94

answer

0.85

 affirmative

0.81

YES

0.80

yes

0.79

 answer

0.78

QUI

0.77

 answ

0.74

 answers

0.73

Activations Density 0.141%

answers or responses within a sentence

assertions or statements that present information or answers

No Comments

No Known Activations