INDEX

Explanations

references to specific entities or notable occurrences

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

 pinulongan

-0.70

henge

-0.69

 invokingState

-0.63

CodeAnalysis

-0.61

 resourceCulture

-0.61

MethodManager

-0.61

GIVEREF

-0.60

GEBURTSDATUM

-0.60

essica

-0.60

surate

-0.59

POSITIVE LOGITS

脚注の使い方

0.59

TabStop

0.53

urlpatterns

0.51

 pared

0.48

named

0.48

ių

0.47

This

0.46

 "/";

0.46

__":

0.45

laughs

0.45

Activations Density 0.354%

references to specific entities or notable occurrences

No Comments

No Known Activations