INDEX

Explanations

occurrences of function definitions and invocations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Datuak

-0.88

ImageContext

-0.85

 referenties

-0.82

 propOrder

-0.81

 NSCoder

-0.79

 disambiguazione

-0.78

 nakalista

-0.77

matum

-0.74

 Himo

-0.74

 saites

-0.74

POSITIVE LOGITS

(__

0.98

lamo

0.76

(__

0.73

(!__

0.70

 McNally

0.69

SourceChecksum

0.69

างเกง

0.67

ventory

0.66

*__

0.66

 purpoſe

0.66

Activations Density 0.043%

occurrences of function definitions and invocations in code

No Comments

No Known Activations