INDEX

Explanations

references to specific variables and mathematical expressions

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

parsedMessage

-0.96

SourceChecksum

-0.89

principalTable

-0.83

AddTagHelper

-0.81

awtextra

-0.78

WriteTagHelper

-0.77

bewerken

-0.74

 дописавши

-0.72

AndEndTag

-0.71

__*/

-0.71

POSITIVE LOGITS

 udaler

0.51

 meub

0.49

 matar

0.43

MoveNext

0.42

therin

0.42

 queda

0.42

 étn

0.41

 colgar

0.41

 gestes

0.41

 blod

0.38

Activations Density 0.631%

references to specific variables and mathematical expressions

No Comments

No Known Activations