INDEX

Explanations

terms related to alpha and beta proteins, specifically in biochemical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

IDEA

-0.54

soort

-0.54

pla

-0.48

 Depp

-0.48

JEE

-0.47

ela

-0.47

findById

-0.46

FTFY

-0.46

 Substance

-0.46

AutoField

-0.45

POSITIVE LOGITS

betic

0.98

betical

0.75

LookAnd

0.73

tagHelperRunner

0.68

psilon

0.68

retta

0.68

djangoproject

0.67

complexContent

0.66

 Sigma

0.65

 Condé

0.64

Activations Density 0.478%

terms related to alpha and beta proteins, specifically in biochemical contexts

No Comments

No Known Activations