INDEX

Explanations

historical references related to laws and legal cases

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

setTarget

-0.65

貼

-0.65

principalColumn

-0.65

nappropriate

-0.61

gruppen

-0.61

RAINT

-0.60

unnitel

-0.58

μό

-0.58

 targeted

-0.58

 McKnight

-0.57

POSITIVE LOGITS

expandindo

0.74

mybatisplus

0.68

twimg

0.64

 sepia

0.63

WWI

0.63

 suffrage

0.60

 Bertha

0.59

 railways

0.59

 dago

0.58

 Maud

0.58

Activations Density 0.723%

historical references related to laws and legal cases

No Comments

No Known Activations