INDEX

Explanations

coding structures or patterns related to function definitions and parameters

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

Code snippets or program names

np_acts-logits-general · gemini-2.0-flash

programming string concatenations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.54

-0.51

-0.49

 None

-0.48

 geçi

-0.43

None

-0.43

جوايز

-0.42

Hybrid

-0.41

POSITIVE LOGITS

DockStyle

0.97

Tikang

0.90

MLLoader

0.89

iastes

0.69

interopRequire

0.67

ponses

0.65

intios

0.65

pholes

0.64

openzeppelin

0.64

WithIOException

0.63

Activations Density 0.071%

coding structures or patterns related to function definitions and parameters

Code snippets or program names

programming string concatenations

No Comments

No Known Activations