INDEX

Explanations

terms related to legal and ethical concepts

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 consultato

-0.50

 mực

-0.44

Библи

-0.43

codecs

-0.42

 agama

-0.42

 shaman

-0.41

ksesta

-0.41

 ratón

-0.41

ydı

-0.41

 skolen

-0.40

POSITIVE LOGITS

 CreateTagHelper

1.00

 AssemblyCulture

0.90

 ModelExpression

0.84

+#+

0.82

 defaultstate

0.80

tagHelperRunner

0.75

 برانيه

0.73

nodoc

0.73

SourceChecksum

0.73

LookAnd

0.72

Activations Density 0.018%

terms related to legal and ethical concepts

No Comments

No Known Activations