INDEX

Explanations

symbols or tokens that indicate programming or coding structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 snippetHide

-0.57

,:);

-0.54

 toJson

-0.51

__*/

-0.50

\"></

-0.49

endregion

-0.49

cshtml

-0.48

tagHelperRunner

-0.47

DllImport

-0.47

 iprot

-0.47

POSITIVE LOGITS

RTEE

0.60

 према

0.56

 AssemblyCompany

0.52

งาม

0.52

ondissement

0.49

tets

0.49

iserie

0.49

 Therapeutics

0.49

isé

0.49

Дереккөздер

0.48

Activations Density 0.234%

symbols or tokens that indicate programming or coding structures

No Comments

No Known Activations