INDEX

Explanations

information related to actors, producers, roles, and movies, including awards and popular titles they are associated with

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Phys

-0.78

Registration

-0.76

Asked

-0.76

BIP

-0.73

Study

-0.72

/>

-0.71

aucus

-0.71

SPONSORED

-0.70

 Accessed

-0.68

)]

-0.66

POSITIVE LOGITS

 collaborations

1.12

 classics

1.12

 titles

1.03

 acclaimed

1.02

 stint

1.01

 films

0.98

 roles

0.96

 seminal

0.96

 productions

0.96

 albums

0.94

Activations Density 0.436%

information related to actors, producers, roles, and movies, including awards and popular titles they are associated with

No Comments

No Known Activations