INDEX

Explanations

contexts related to observed behavior and interactions among multiple characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

into

-0.43

 propre

-0.43

Own

-0.41

Sy

-0.41

specific

-0.41

own

-0.40

getFullYear

-0.40

Suffix

-0.39

ான

-0.39

conoc

-0.38

POSITIVE LOGITS

ConstraintMaker

0.86

tagext

0.86

 typelib

0.86

ScopeManager

0.86

 invokingState

0.83

Попис

0.80

 disambiguazione

0.78

DoubleQuotes

0.77

 ExecuteAsync

0.76

TargetException

0.75

Activations Density 0.239%

contexts related to observed behavior and interactions among multiple characters

No Comments

No Known Activations