INDEX

Explanations

references to high levels or qualities in various 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

AnchorStyles

-0.58

 ramai

-0.58

 fatica

-0.58

 beira

-0.56

FTFY

-0.54

 mús

-0.53

ódz

-0.53

########.

-0.53

 étoient

-0.52

artifactId

-0.50

POSITIVE LOGITS

 degree

0.80

IntoConstraints

0.73

 level

0.68

 priced

0.65

jacking

0.65

lighed

0.64

 probability

0.64

brow

0.64

 levels

0.64

 priority

0.62

Activations Density 0.229%

references to high levels or qualities in various contexts

No Comments

No Known Activations