INDEX

Explanations

references to user interface components and data structures 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 @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

</h2>

-0.58

PyExc

-0.51

onnay

-0.49

kel

-0.46

 Kelley

-0.45

-0.44

 schlägt

-0.43

Kel

-0.42

</h4>

-0.42

rypt

-0.41

POSITIVE LOGITS

ⓧ

1.03

SequentialGroup

0.94

AddHtmlAttribute

0.89

 surla

0.82

 propOrder

0.81

 GetEnumerator

0.76

ChildScrollView

0.75

ImageContext

0.74

tagHelperRunner

0.72

HasAnnotation

0.71

Activations Density 0.024%

references to user interface components and data structures in programming contexts

No Comments

No Known Activations