INDEX

Explanations

examples or instances of behaviors or characteristics

oai_token-act-pair · gpt-3.5-turbo

instances of examples being cited in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Enlarge

-0.74

hunt

-0.72

ettes

-0.70

emies

-0.68

forts

-0.67

EEP

-0.65

task

-0.65

querade

-0.65

agues

-0.65

culosis

-0.64

POSITIVE LOGITS

how

1.37

why

1.29

 what

0.97

 hypocrisy

0.94

 unintended

0.89

why

0.88

how

0.87

 lazy

0.87

WHY

0.83

 misplaced

0.82

Activations Density 0.115%

examples or instances of behaviors or characteristics

instances of examples being cited in various contexts

No Comments

No Known Activations