INDEX

Explanations

special characters or symbols used in data labeling or formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

principalColumn

-0.79

varargin

-0.76

AddHtmlAttribute

-0.70

 vectorielle

-0.70

 InputDecoration

-0.68

TagMode

-0.68

InputBorder

-0.67

LLocation

-0.67

 BoxDecoration

-0.66

addContainerGap

-0.66

POSITIVE LOGITS

0.55

0.50

en

0.47

0.46

back

0.44

0.43

with

0.43

/_

0.43

Activations Density 0.274%

special characters or symbols used in data labeling or formatting

No Comments

No Known Activations