INDEX

Explanations

references to adaptations of various works into different formats

oai_token-act-pair · gpt-3.5-turbo

references to adaptations of various forms of media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

apse

-0.83

etsk

-0.80

mouth

-0.77

pants

-0.72

dash

-0.71

nuts

-0.70

Cola

-0.67

adows

-0.67

hair

-0.66

acia

-0.66

POSITIVE LOGITS

 adaptation

1.24

 adaptations

0.97

 screenplay

0.89

 thereof

0.78

 adapted

0.78

adapt

0.73

arium

0.71

ãĥ¯

0.71

 adapting

0.69

 Adapt

0.69

Activations Density 0.018%

references to adaptations of various works into different formats

references to adaptations of various forms of media

No Comments

No Known Activations