INDEX

Explanations

references to processing in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

帖最后由

-0.96

RegressionTest

-0.94

EndProject

-0.85

'));

-0.81

(!__

-0.79

 propOrder

-0.78

__':

-0.76

IsContent

-0.74

LLocation

-0.74

')):

-0.72

POSITIVE LOGITS

 processing

0.74

we

0.57

fs

0.56

 Processing

0.55

processing

0.54

mel

0.54

 proceedings

0.52

 PROCESSING

0.52

которы

0.51

 tapete

0.50

Activations Density 0.157%

references to processing in various contexts

No Comments

No Known Activations