INDEX

Explanations

phrases indicating a continuation or transition in speech or writing, often introducing new information or emphasizing a point

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 DISTR

-0.76

CPR

-0.59

 Mobil

-0.59

 pulp

-0.58

 bluff

-0.58

 shack

-0.58

 Mirage

-0.57

RAD

-0.57

 Monkey

-0.57

 Monroe

-0.57

POSITIVE LOGITS

Pg

0.86

ttp

0.79

shall

0.77

aternity

0.77

ould

0.76

ept

0.75

¼

0.74

else

0.73

ı

0.72

Activations Density 0.137%

phrases indicating a continuation or transition in speech or writing, often introducing new information or emphasizing a point

No Comments

No Known Activations