INDEX

Explanations

references to online forums and discussions

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

Forum-related content

np_acts-logits-general · gemini-2.0-flash

forum and threads discussions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Bibliograf

-0.65

setVerticalGroup

-0.58

ynb

-0.55

corporate

-0.54

stateProvider

-0.54

numerusform

-0.53

кономі

-0.53

Tikang

-0.51

ActionCreators

-0.51

utnik

-0.50

POSITIVE LOGITS

 forum

1.09

 forums

1.08

 Forums

0.94

 threads

0.92

 Forum

0.90

Forum

0.88

forum

0.85

 FORUM

0.82

threads

0.80

Threads

0.80

Activations Density 0.150%

references to online forums and discussions

Forum-related content

forum and threads discussions

No Comments

No Known Activations