INDEX

Explanations

code-related constructs and elements in programming syntax

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

 myſelf

-0.82

StructEnd

-0.79

Hochspringen

-0.78

fjspx

-0.78

Personendaten

-0.77

 cauſe

-0.76

Personensuche

-0.76

 itſelf

-0.75

 Theſe

-0.74

 ſtate

-0.73

POSITIVE LOGITS

 surla

0.66

 Wiktionnaire

0.63

Edm

0.46

<eos>

0.45

ercizio

0.44

र्जा

0.44

):

0.44

bashrc

0.43

ெ

0.43

وفة

0.43

Activations Density 0.243%

code-related constructs and elements in programming syntax

No Comments

No Known Activations