INDEX

Explanations

specific categories and classifications in structured data, particularly related to biological, academic, and programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

zelfde

-0.83

sweise

-0.75

iyle

-0.72

ه

-0.66

 يتيمه

-0.66

ième

-0.66

یتی

-0.65

iarkan

-0.64

يته

-0.63

iqué

-0.63

POSITIVE LOGITS

<bos>

2.27

JKLM

0.68

ekš

0.68

vény

0.63

yszer

0.60

 الاول

0.59

pośred

0.57

 שח

0.56

çası

0.55

lső

0.54

Activations Density 5.969%

specific categories and classifications in structured data, particularly related to biological, academic, and programming contexts

No Comments

No Known Activations