INDEX

Explanations

references or citations within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Hoffman

-0.78

ally

-0.73

 Kaufman

-0.71

unately

-0.68

authToken

-0.67

 Morton

-0.67

knapp

-0.67

xter

-0.66

ASTER

-0.66

getInput

-0.66

POSITIVE LOGITS

 Sees

1.45

See

1.41

SEE

1.37

see

1.34

See

1.33

see

1.28

SEE

1.25

 sees

1.20

sees

1.06

Sce

0.96

Activations Density 0.083%

references or citations within a document

No Comments

No Known Activations