INDEX

Explanations

words related to physical objects or features, specifically items with hooks or buttons

oai_token-act-pair · gpt-3.5-turbo

terms related to physical or metaphorical hooks and buttons 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Operation

-0.76

lier

-0.74

Hur

-0.71

oÄŁ

-0.68

scape

-0.65

Delivery

-0.64

Iraq

-0.64

ABLE

-0.64

Austral

-0.64

ZE

-0.64

POSITIVE LOGITS

mith

1.67

paces

1.58

pace

1.47

hops

1.44

poons

1.39

creen

1.36

hips

1.32

ettings

1.31

uggest

1.27

heet

1.25

Activations Density 0.136%

words related to physical objects or features, specifically items with hooks or buttons

terms related to physical or metaphorical hooks and buttons in various contexts

No Comments

No Known Activations