INDEX

Explanations

indicators of academic studies or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

“

-0.61

-0.57

„

-0.49

 (“

-0.48

("

-0.48

 Weiss

-0.47

 carbon

-0.47

cono

-0.45

nolo

-0.45

POSITIVE LOGITS

DeleteBehavior

0.90

AutoScaleMode

0.90

RegressionTest

0.89

 AssemblyTitle

0.88

ValueGeneration

0.84

+#+#

0.83

Tikang

0.83

NameInMap

0.81

évaluateur

0.81

writeFieldEnd

0.81

Activations Density 0.292%

indicators of academic studies or reports

No Comments

No Known Activations