INDEX

Explanations

terms related to government regulations and permissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

CodeAttribute

-0.66

MLLoader

-0.63

Viited

-0.60

 AssemblyCulture

-0.59

ability

-0.58

itinéraire

-0.56

pital

-0.56

Pautan

-0.56

 høre

-0.55

plane

-0.55

POSITIVE LOGITS

mable

0.91

mmm

0.78

mers

0.77

med

0.69

mi

0.67

ming

0.67

mmmm

0.66

 ***!

0.65

MING

0.64

selfish

0.64

Activations Density 1.306%

terms related to government regulations and permissions

No Comments

No Known Activations