INDEX

Explanations

references to movies and media lists

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

add or remove from collection

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 constater

-0.39

ugy

-0.38

 EXIST

-0.38

íslu

-0.37

 Leib

-0.37

 saurait

-0.36

 chrétien

-0.36

 nahilalakip

-0.35

 mourir

-0.35

 houve

-0.34

POSITIVE LOGITS

 thrown

0.69

 transferred

0.69

 placed

0.68

 pushed

0.65

 kept

0.61

 dragged

0.58

 replaced

0.57

 squeezed

0.57

 turned

0.57

 knocked

0.56

Activations Density 0.002%

references to movies and media lists

add or remove from collection

No Comments

No Known Activations