INDEX

Explanations

comments and documentation tags in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

WithIOException

-0.67

 AssemblyCulture

-0.63

MigrationBuilder

-0.56

FieldNumber

-0.53

kháu

-0.52

comb

-0.50

Composable

-0.48

DockStyle

-0.48

ldc

-0.47

AccessorTable

-0.46

POSITIVE LOGITS

 Vikipedi

0.73

 متعلقه

0.68

atase

0.65

 мәкалә

0.61

 bezeichneter

0.59

UserScript

0.58

SourceChecksum

0.58

httphttps

0.58

principalTable

0.57

mtable

0.55

Activations Density 0.036%

comments and documentation tags in code

No Comments

No Known Activations