INDEX

Explanations

the word "one" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

tvguidetime

-0.91

__':

-0.82

 doInBackground

-0.76

ChildScrollView

-0.73

例句

-0.71

principalTable

-0.70

__":

-0.69

الحياه

-0.66

stdc

-0.66

dures

-0.66

POSITIVE LOGITS

one

0.79

One

0.66

One

0.64

ONE

0.62

one

0.61

ThroughAttribute

0.59

ख्या

0.53

ONE

0.47

 één

0.47

sidenav

0.47

Activations Density 0.141%

the word "one" in various contexts

No Comments

No Known Activations