INDEX

Explanations

technical terms related to electronics and genetic research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 itſelf

-1.37

 myſelf

-1.35

Efq

-1.28

 Majefty

-1.24

 themſelves

-1.23

 Theſe

-1.23

 Monfieur

-1.17

 becauſe

-1.15

 Shakspeare

-1.15

 Jefus

-1.13

POSITIVE LOGITS

mer

0.73

mer

0.67

 nach

0.66

Mer

0.65

MER

0.65

dit

0.63

Mer

0.60

MER

0.59

ا

0.57

ties

0.57

Activations Density 2.875%

technical terms related to electronics and genetic research

No Comments

No Known Activations