INDEX

Explanations

elements related to legal verdicts and proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

col

-2.02

Col

-2.00

Col

-1.90

COL

-1.79

col

-1.79

 Coll

-1.68

 COLL

-1.66

COL

-1.66

coll

-1.62

kol

-1.60

POSITIVE LOGITS

 esternos

0.61

 nudo

0.60

 Spisak

0.60

forChild

0.55

SourceChecksum

0.50

 Aphrodite

0.50

 traseiro

0.48

 WebDriverWait

0.48

ecake

0.48

يميديا

0.48

Activations Density 0.183%

elements related to legal verdicts and proceedings

No Comments

No Known Activations