INDEX

Explanations

code-related terms and functions associated with data encoding and decoding processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 ModelExpression

-0.62

FunctionFlags

-0.60

otka

-0.54

ThroughAttribute

-0.52

 onlyOwner

-0.48

HCM

-0.47

holland

-0.47

delwed

-0.47

hab

-0.46

IntoConstraints

-0.46

POSITIVE LOGITS

 للمعارف

0.80

📻

0.76

νώ

0.72

jsonwebtoken

0.68

losures

0.66

 صوتيه

0.65

tears

0.64

ulgação

0.63

szcz

0.61

likace

0.60

Activations Density 0.086%

code-related terms and functions associated with data encoding and decoding processes

No Comments

No Known Activations