INDEX

Explanations

references to mathematical or programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

)|^{

-0.86

WEBPACK

-0.78

iaomi

-0.77

uzzi

-0.76

ugeot

-0.76

latform

-0.72

 Schar

-0.72

Gom

-0.71

ALLEL

-0.71

COMM

-0.71

POSITIVE LOGITS

StructEnd

0.85

MessageTagHelper

0.79

 Chwiliwch

0.76

مراجع

0.74

principalTable

0.74

aarrggbb

0.72

ButterKnife

0.70

thâu

0.64

 שוליים

0.62

ArrowToggle

0.60

Activations Density 0.399%

references to mathematical or programming constructs

No Comments

No Known Activations