INDEX

Explanations

references to data schemas and configurations within a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.78

Portale

-0.78

EndGlobalSection

-0.75

IndentedString

-0.68

AppMethodBeat

-0.63

ViewFeatures

-0.61

chartInstance

-0.60

hoeddwyd

-0.56

*>(

-0.56

 beginnetje

-0.56

POSITIVE LOGITS

DoubleQuotes

0.67

 تانيه

0.67

tvguidetime

0.60

 متعلقه

0.58

PerformLayout

0.53

naio

0.52

 NSCoder

0.52

 nonché

0.52

 snippetHide

0.51

SuspendLayout

0.50

Activations Density 0.183%

references to data schemas and configurations within a coding context

No Comments

No Known Activations