INDEX

Explanations

references to documents, sources, or links often associated with legal or academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ConstraintMaker

-0.67

 nakalista

-0.62

 propOrder

-0.61

aarrggbb

-0.60

 سكانية

-0.58

#+#

-0.57

SuppressMessage

-0.56

argb

-0.56

----</

-0.55

Vidite

-0.53

POSITIVE LOGITS

 kasarigan

0.59

TypedDataSet

0.58

ParseTree

0.57

!("{}",

0.56

 typelib

0.55

HideFlags

0.54

ibn

0.53

 мәкалә

0.53

Personendaten

0.51

 Connectez

0.50

Activations Density 0.494%

references to documents, sources, or links often associated with legal or academic contexts

No Comments

No Known Activations