INDEX

Explanations

words related to actions or commands such as 'backing', 'tracked', 'kicking', 'ducks'

oai_token-act-pair · gpt-3.5-turbo

words related to debt and financial obligations

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

enegger

-0.78

EVA

-0.70

issance

-0.69

 Trance

-0.68

 TODAY

-0.67

imov

-0.65

enment

-0.64

ITED

-0.64

endez

-0.62

oir

-0.62

POSITIVE LOGITS

oshenko

0.99

edo

0.86

bones

0.85

 torches

0.84

bits

0.79

uyomi

0.78

bon

0.73

pointers

0.71

boxes

0.71

pole

0.70

Activations Density 0.061%

words related to actions or commands such as 'backing', 'tracked', 'kicking', 'ducks'

words related to debt and financial obligations

No Comments

No Known Activations