INDEX

Explanations

the keyword "out"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 AssemblyCulture

-0.69

 propOrder

-0.56

RegressionTest

-0.56

 Photocase

-0.54

 rhestr

-0.54

Ранее

-0.51

 Савезне

-0.50

 kohdetta

-0.49

EndProject

-0.48

 continúas

-0.46

POSITIVE LOGITS

out

1.34

OUT

0.85

Out

0.79

OUT

0.74

Out

0.74

out

0.73

outs

0.70

oute

0.65

DOUT

0.59

 outs

0.57

Activations Density 0.050%

the keyword "out"

No Comments

No Known Activations