INDEX

Explanations

references to medical or scientific parameters related to testing and results analysis

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

principalColumn

-0.84

UIControlState

-0.75

"):

-0.72

 resourceCulture

-0.69

\{\\

-0.69

CppCodeGen

-0.68

 Drapeau

-0.68

}))

-0.65

">${

-0.64

guenos

-0.64

POSITIVE LOGITS

0.71

又は

0.59

0.57

}/

0.56

 charité

0.54

/-

0.53

 phép

0.51

或

0.50

あるいは

0.48

 sagesse

0.48

Activations Density 0.347%

references to medical or scientific parameters related to testing and results analysis

No Comments

No Known Activations