INDEX

Explanations

content related to binary outcomes or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 CanadaChoose

-0.70

 utafitiHapana

-0.70

^(@)

-0.69

참고

-0.69

||=

-0.67

EventQueue

-0.67

utilisons

-0.66

uttgart

-0.66

انجليز

-0.65

".

-0.65

POSITIVE LOGITS

tagHelperRunner

0.55

IntoConstraints

0.53

ruptedException

0.49

0.46

0.44

↵

0.44

↵↵

0.42

 AssemblyCulture

0.42

 ModelExpression

0.41

Activations Density 1.581%

content related to binary outcomes or states

No Comments

No Known Activations