INDEX

Explanations

statistical terms and references to analysis 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 @ 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

Abitanti

-0.71

 dessas

-0.62

 desses

-0.59

 ihres

-0.59

❋

-0.57

 gewor

-0.55

empêcher

-0.55

及其

-0.54

einem

-0.54

 Ihres

-0.53

POSITIVE LOGITS

the

3.26

the

0.66

rethe

0.62

 την

0.60

 τη

0.56

tothe

0.55

ofthe

0.53

private

0.53

enthe

0.51

ethe

0.51

Activations Density 8.215%

statistical terms and references to analysis in various contexts

No Comments

No Known Activations