INDEX

Explanations

contrasting statements or qualifiers that introduce alternative perspectives

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ActionCreators

-0.55

 immerhin

-0.53

ceps

-0.52

uens

-0.51

IInterface

-0.51

 Präsidenten

-0.50

 masukkan

-0.50

 uova

-0.49

 wicket

-0.48

Продам

-0.48

POSITIVE LOGITS

 NSCoder

0.76

DeleteBehavior

0.67

SuppressMessage

0.64

complexContent

0.62

DebuggerNonUser

0.59

 subtle

0.59

 autorytatywna

0.56

^(@

0.55

 focus

0.55

-------------</

0.54

Activations Density 0.225%

contrasting statements or qualifiers that introduce alternative perspectives

No Comments

No Known Activations