INDEX

Explanations

terms and concepts related to categorization and classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Exactos

-0.61

protoimpl

-0.51

nasel

-0.49

lju

-0.48

urum

-0.48

多分

-0.48

eclamp

-0.47

 виправивши

-0.46

맷

-0.46

↵↵↵↵

-0.45

POSITIVE LOGITS

 AssemblyCulture

0.72

ContentAsync

0.57

とは

0.56

 hâte

0.56

 refers

0.56

 chaude

0.55

UnsafeEnabled

0.54

 träd

0.54

InjectAttribute

0.52

 antemano

0.52

Activations Density 0.658%

terms and concepts related to categorization and classification

No Comments

No Known Activations