INDEX

Explanations

specific nouns and components related to various subjects, including biology and legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Normdatei

-0.73

SourceChecksum

-0.71

 alcuna

-0.70

riwal

-0.69

 réfrig

-0.67

iconque

-0.67

 nemici

-0.66

 AssemblyCompany

-0.65

pexpr

-0.65

 engraçadas

-0.65

POSITIVE LOGITS

 including

0.47

SaveChangesAsync

0.44

 gồm

0.42

Including

0.42

xton

0.41

 interrelated

0.40

üyor

0.39

бята

0.38

ittu

0.38

ीन

0.38

Activations Density 0.492%

specific nouns and components related to various subjects, including biology and legal contexts

No Comments

No Known Activations