INDEX

Explanations

method definitions and initializations within class structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

LookAnd

-0.89

Portale

-0.84

 Burnham

-0.68

Portály

-0.63

lained

-0.63

bibit

-0.61

 Hearst

-0.60

ϊ

-0.58

 Alca

-0.58

amoan

-0.58

POSITIVE LOGITS

__(

1.35

consulté

0.90

RetentionPolicy

0.79

ագրություններ

0.73

tagHelperRunner

0.72

 المعرف

0.66

HtmlAttribute

0.65

θρω

0.63

IsContent

0.63

ConstraintMaker

0.60

Activations Density 0.016%

method definitions and initializations within class structures

No Comments

No Known Activations