INDEX

Explanations

phrases that indicate specific examples or elaborations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Fail

-0.48

fail

-0.47

ContextHolder

-0.46

沿革

-0.45

 presentazione

-0.45

 policiales

-0.45

пите

-0.42

ItemBackground

-0.42

 profesión

-0.41

 Mood

-0.41

POSITIVE LOGITS

RetentionPolicy

0.71

Efq

0.70

Hozzáférés

0.66

getMenuInflater

0.65

yczą

0.61

AnimationsModule

0.61

فایل‌لار

0.60

 esternos

0.59

 onix

0.59

 geox

0.58

Activations Density 0.825%

phrases that indicate specific examples or elaborations

No Comments

No Known Activations