INDEX

Explanations

instances of return statements in code, specifically associated with function outputs

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

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

 AssemblyCompany

-0.79

 onPage

-0.57

Demografie

-0.57

ليق

-0.57

stellen

-0.56

 avsl

-0.55

épisode

-0.55

CharStream

-0.55

 desear

-0.53

 Ucraina

-0.53

POSITIVE LOGITS

 Returns

0.72

 home

0.71

eturn

0.69

 indietro

0.68

Returns

0.67

 returns

0.66

 مشين

0.65

BASEPATH

0.65

 pulumi

0.64

RETURNS

0.64

Activations Density 0.097%

instances of return statements in code, specifically associated with function outputs

No Comments

No Known Activations