INDEX

Explanations

structured programming elements such as templates and views in code snippets

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

MethodManager

-0.69

writeFieldEnd

-0.66

 betweenstory

-0.56

WritableDatabase

-0.56

FailureListener

-0.55

GraphicsUnit

-0.54

 XCTest

-0.54

الحياه

-0.53

uestamente

-0.53

 wymiar

-0.52

POSITIVE LOGITS

 template

1.17

template

1.09

 templates

1.06

Template

1.03

 Template

1.00

模板

0.93

 Templates

0.93

tmpl

0.93

templates

0.91

 模板

0.90

Activations Density 0.271%

structured programming elements such as templates and views in code snippets

No Comments

No Known Activations