INDEX

Explanations

terms related to programming elements, particularly identifiers and properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-1.00

TagHelpers

-0.76

-0.69

-0.68

-0.67

-0.66

POSITIVE LOGITS

 purpoſe

1.55

 myſelf

1.54

 themſelves

1.48

 raiſ

1.46

 himſelf

1.45

 Theſe

1.43

 uſed

1.42

 fubject

1.41

ſelf

1.39

 Anſ

1.34

Activations Density 0.226%

terms related to programming elements, particularly identifiers and properties

No Comments

No Known Activations