INDEX

Explanations

references to historical or significant events

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

Followed by numbers or uncommon words

np_acts-logits-general · gemini-2.0-flash

though labor

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Wikimedijinoj

-0.59

","\

-0.59

வு

-0.57

Попис

-0.51

<#

-0.50

rungsseite

-0.49

)++;

-0.49

mentet

-0.49

isbury

-0.49

indsay

-0.48

POSITIVE LOGITS

↵↵↵

0.61

↵

0.57

AddTagHelper

0.56

StackNavigator

0.52

 recargable

0.51

 перево

0.51

 GenerationType

0.50

openqa

0.48

UseVisualStyle

0.48

Tikang

0.48

Activations Density 0.087%

references to historical or significant events

Followed by numbers or uncommon words

though labor

No Comments

No Known Activations