INDEX

Explanations

calls to the plotting library in programming contexts

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

LookAnd

-0.92

GraphicsUnit

-0.88

GEBURTSDATUM

-0.83

 архивлан

-0.79

principalTable

-0.78

rungsseite

-0.78

 للاسماء

-0.77

ThroughAttribute

-0.76

MessageOf

-0.76

TestingModule

-0.73

POSITIVE LOGITS

%";

0.56

text

0.42

 appreciate

0.42

inctive

0.40

 appreciated

0.39

 mát

0.39

城堡

0.39

وصلات

0.39

 streak

0.39

ht

0.39

Activations Density 0.062%

calls to the plotting library in programming contexts

No Comments

No Known Activations