INDEX

Explanations

references to specific names or identifiers, particularly in academic or entertainment contexts

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

 autorytatywna

-0.68

 inverse

-0.54

ViewImports

-0.53

Msp

-0.52

таратура

-0.52

ktop

-0.49

::::::::

-0.49

Personendaten

-0.49

AccessFile

-0.49

 initComponents

-0.49

POSITIVE LOGITS

 iArr

0.72

 isNameExpr

0.64

lohn

0.63

dyž

0.60

 shards

0.59

 pinggang

0.59

 Elba

0.59

ographique

0.59

 برانيه

0.59

ydable

0.57

Activations Density 0.487%

references to specific names or identifiers, particularly in academic or entertainment contexts

No Comments

No Known Activations