INDEX

Explanations

references to legal or court-related terms and 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-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

-0.96

-0.93

-0.88

-0.85

-0.84

-0.82

-0.78

-0.76

esh

-0.72

POSITIVE LOGITS

IIA

1.11

II

1.11

II

1.09

 متعلقه

1.07

III

1.06

 dynasties

1.05

IIII

1.04

 ويكيميديا

1.03

wii

0.98

 VIII

0.94

Activations Density 0.099%

references to legal or court-related terms and concepts

No Comments

No Known Activations