INDEX

Explanations

frequent pronouns and indicators of confidence or existence in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 himſelf

-0.63

 themſelves

-0.59

Efq

-0.55

 myſelf

-0.54

ſelf

-0.54

 whoſe

-0.50

 ſame

-0.48

 Soyez

-0.48

 Hamma

-0.48

 greateſt

-0.48

POSITIVE LOGITS

KommentareTeilen

0.83

DataAnnotations

0.77

httphttps

0.73

Và

0.73

 виправивши

0.71

InSection

0.71

出版年

0.69

SequentialGroup

0.68

BURGH

0.66

NSUserDefaults

0.65

Activations Density 0.188%

frequent pronouns and indicators of confidence or existence in statements

No Comments

No Known Activations