INDEX

Explanations

mentions of "fe" as a prefix in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 виправивши

-0.75

 Basta

-0.63

 autorytatywna

-0.63

 kasarigan

-0.61

parsedMessage

-0.60

сылкі

-0.58

WriteLiteral

-0.56

govine

-0.56

zheimer

-0.55

RenderAtEndOf

-0.55

POSITIVE LOGITS

Fe

1.08

Fe

1.07

fe

0.97

FE

0.90

FE

0.83

 Felicia

0.80

fe

0.77

fees

0.76

fee

0.73

Fee

0.73

Activations Density 0.125%

mentions of "fe" as a prefix in a variety of contexts

No Comments

No Known Activations