INDEX

Explanations

occurrences of significant quantitative measures or milestones in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

พาะ

-0.53

previously

-0.51

 previously

-0.49

 contraire

-0.48

其中

-0.48

 previous

-0.48

 annen

-0.48

 PREVIOUS

-0.47

ranges

-0.47

一時

-0.47

POSITIVE LOGITS

 ever

1.06

 EVER

0.89

ever

0.84

RenderAtEndOf

0.83

 ooit

0.80

Ever

0.77

 Ever

0.74

 überhaupt

0.72



0.66

HasAnnotation

0.65

Activations Density 0.359%

occurrences of significant quantitative measures or milestones in various contexts

No Comments

No Known Activations