INDEX

Explanations

terms related to legal concepts and judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Alexandre

-0.61

✨:

-0.61

CodeAnalysis

-0.60

ebx

-0.60

 McNeil

-0.59

lec

-0.59

 Consiglio

-0.59

Leaky

-0.59

 plati

-0.58

 Magi

-0.58

POSITIVE LOGITS

in

1.06

 therein

0.98

 Maß

0.85

 pleaſure

0.81

 himſelf

0.81

 involved

0.81

 AssemblyCulture

0.80

 purpoſe

0.78

hyrchwyd

0.78

 myſelf

0.78

Activations Density 0.849%

terms related to legal concepts and judgments

No Comments

No Known Activations