INDEX

Explanations

legal terminology and references to court cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WriteTagHelper

-0.72

MemoryWarning

-0.66

AutoScaleMode

-0.64

SpringBootTest

-0.60

 NSCoder

-0.57

енча

-0.56

ogaster

-0.56

ImageContext

-0.56

gonic

-0.54

Personendaten

-0.52

POSITIVE LOGITS

 district

0.89

 District

0.77

district

0.75

 Eastern

0.70

District

0.69

 federal

0.65

 Northern

0.65

 Southern

0.60

DISTRICT

0.60

Eastern

0.59

Activations Density 2.413%

legal terminology and references to court cases

No Comments

No Known Activations