INDEX

Explanations

negative descriptors and terms related to crime and punishment

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

 Bourgoin

-0.90

IUrlHelper

-0.80

databind

-0.74

WireFormatLite

-0.73

GOTREF

-0.73

 Laing

-0.70

AndEndTag

-0.70

adaptiveStyles

-0.69

rijke

-0.69

,‎

-0.68

POSITIVE LOGITS

 worse

1.35

Worse

1.21

BAD

1.20

bad

1.16

 Worse

1.16

 worst

1.16

Bad

1.15

Bad

1.12

worse

1.11

bad

1.10

Activations Density 0.132%

negative descriptors and terms related to crime and punishment

No Comments

No Known Activations