INDEX

Explanations

technical terms related to genetic and genomic sequences

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

tory

-0.93

 Tsche

-0.81

 Woodbury

-0.81

gory

-0.78

 Hauser

-0.73

 NSCoder

-0.72

spacer

-0.72

 Czechos

-0.71

adecimal

-0.70

triangleq

-0.69

POSITIVE LOGITS

in

1.40

IN

1.34

nnnn

1.22

qin

1.18

vin

1.17

Zin

1.17

rin

1.16

nin

1.16

HIN

1.14

Zin

1.11

Activations Density 0.686%

technical terms related to genetic and genomic sequences

No Comments

No Known Activations