INDEX

Explanations

specific criteria used for evaluation or classification in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ViewFeatures

-0.79

 otomatig

-0.75

 shocks

-0.73

KommentareTeilen

-0.65

ressum

-0.64

ніципалі

-0.63

 protons

-0.63

///</

-0.62

TypedDataSet

-0.62

]='\

-0.60

POSITIVE LOGITS

 criteria

2.75

 Criteria

2.41

criteria

2.38

 CRITERIA

2.22

Criteria

2.18

 criterion

2.03

 critères

1.68

 criter

1.67

 criterio

1.59

 Kriterien

1.56

Activations Density 0.074%

specific criteria used for evaluation or classification in various contexts

No Comments

No Known Activations