INDEX

Explanations

references to text and its manipulation in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 fubject

-0.52

feitura

-0.51

uvres

-0.51

 DOWNVOTE

-0.51

igreja

-0.49

wakili

-0.48

Składniki

-0.48

Gweler

-0.48

υτό

-0.48

 reafon

-0.47

POSITIVE LOGITS

Text

2.88

 Text

2.48

text

1.99

TEXT

1.87

 text

1.82

 TEXT

1.73

 textual

1.46

 Texts

1.44

Texts

1.43

文本

1.41

Activations Density 0.040%

references to text and its manipulation in programming

No Comments

No Known Activations