INDEX

Explanations

various technical terms and statistical measures related to analysis and results

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

 <=",

-0.57

BeginContext

-0.56

InitVars

-0.54

+#+#

-0.51

 '\\;'

-0.51

 wisely

-0.50

enumii

-0.50

त्ति

-0.48

 Sist

-0.47

しまいました

-0.46

POSITIVE LOGITS

 AssemblyVersion

0.78

WebServlet

0.57

 usually

0.55

Bioaccumulative

0.54

IndentedString

0.53

usually

0.53

setContentView

0.52

 Usually

0.50

GenerationType

0.50

folgung

0.50

Activations Density 1.201%

various technical terms and statistical measures related to analysis and results

No Comments

No Known Activations