INDEX

Explanations

references to graphical or drawing elements in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-0.98

principalColumn

-0.72

(||

-0.69

róż

-0.66

}{*}{

-0.65

hoeddwyd

-0.64

 major

-0.63

 '\\;'

-0.62

(~(

-0.62

 sonno

-0.62

POSITIVE LOGITS

Drawing

1.59

 Drawing

1.34

 drawing

1.21

drawing

1.08

 drawings

1.05

 DRAWING

1.04

 drawn

1.00

 draws

0.99

 Draws

0.97

 draw

0.94

Activations Density 0.007%

references to graphical or drawing elements in programming contexts

No Comments

No Known Activations