INDEX

Explanations

references to academic journals and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

OGND

-0.71

Ārējās

-0.59

Sparse

-0.56

 Rajah

-0.56

 PICT

-0.55

 bode

-0.54

Kaieteur

-0.54

sizeCache

-0.53

 Elen

-0.50

 martyrs

-0.50

POSITIVE LOGITS

PhysRevLett

0.90

ConstraintMaker

0.82

mybatisplus

0.64

makeConstraints

0.64

IActionResult

0.61

PhysRevD

0.61

StoryboardSegue

0.59

ctools

0.58

AccessorTable

0.58

AutoField

0.56

Activations Density 0.195%

references to academic journals and publications

No Comments

No Known Activations