INDEX

Explanations

specific locations and regional identifiers

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

 lenker

-0.71

Carriera

-0.64

 Gideon

-0.59

 Duggan

-0.57

 Diogo

-0.55

 Ronnie

-0.54

 Lieberman

-0.54

 Eben

-0.53

bootstrapcdn

-0.52

SAE

-0.50

POSITIVE LOGITS

 Kast

1.08

Ost

1.08

 mast

1.06

 Bast

1.04

 Mast

1.04

AST

1.02

 crest

1.02

Mast

1.01

 Brist

1.00

 Rast

1.00

Activations Density 0.471%

specific locations and regional identifiers

No Comments

No Known Activations