INDEX

Explanations

indications or hints of something in a text

oai_token-act-pair · gpt-3.5-turbo

recurring patterns or indicators of a certain situation or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ISH

-0.80

ARY

-0.78

NES

-0.75

âĨĳ

-0.72

UTE

-0.72

UNCH

-0.71

=~=~

-0.70

POSE

-0.70

Sah

-0.70

ASE

-0.69

POSITIVE LOGITS

 signs

1.42

 Signs

1.41

 sign

1.11

igmatic

1.01

 signage

0.88

 Sign

0.86

posts

0.85

sign

0.84

oresc

0.81

achy

0.80

Activations Density 0.009%

indications or hints of something in a text

recurring patterns or indicators of a certain situation or condition

No Comments

No Known Activations