INDEX

Explanations

explicit comparisons and descriptions of variations among subjects or methods

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

enumi

-0.62

 renseignements

-0.61

ExtendWith

-0.59

enumii

-0.52

erda

-0.48

NameInMap

-0.46

NewUrlParser

-0.46

userdetails

-0.45

 AssemblyProduct

-0.44

Bears

-0.44

POSITIVE LOGITS

 specific

0.98

 particular

0.86

 Specific

0.85

specific

0.82

Specific

0.81

 preferred

0.79

 definite

0.78

 bestimmte

0.77

特定的

0.77

 spécifiques

0.76

Activations Density 0.451%

explicit comparisons and descriptions of variations among subjects or methods

No Comments

No Known Activations