INDEX

Explanations

references to illustrations or figures in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

()?;

-0.68

RegressionTest

-0.63

 Superhosts

-0.60

 shelled

-0.59

VolleyError

-0.57

 Casper

-0.56

KURZBESCHREIBUNG

-0.56

:\/\/

-0.55

श्न

-0.55

 nenhum

-0.55

POSITIVE LOGITS

Drawing

3.77

 Drawing

3.21

 drawing

2.92

drawing

2.78

 DRAWING

2.48

 draw

2.31

 draws

2.22

 drew

2.10

 drawings

2.06

 Draws

2.05

Activations Density 0.031%

references to illustrations or figures in a document

No Comments

No Known Activations