INDEX

Explanations

numerical values and specific formats typically seen in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 previous

-0.89

Previous

-0.76

 Previous

-0.76

 earlier

-0.75

 sebelumnya

-0.73

 предыду

-0.71

previous

-0.71

 PREVIOUS

-0.68

PREVIOUS

-0.64

 previously

-0.63

POSITIVE LOGITS

hoeddwyd

0.57

 bianchi

0.51

styleable

0.50

ⓧ

0.49

fit

0.49

 nhật

0.49

Fit

0.49

 CallOverrides

0.47

 comen

0.47

 getItemId

0.47

Activations Density 0.516%

numerical values and specific formats typically seen in scientific or technical contexts

No Comments

No Known Activations