INDEX

Explanations

repeated usage of the word "the" and related structure in textual data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ConstraintMaker

-0.84

AddTagHelper

-0.70

GeneratedMessage

-0.69

Personensuche

-0.68

webElementXpaths

-0.65

CodeAttribute

-0.65

-0.62

íticas

-0.60

RegistryLite

-0.60

};*/

-0.58

POSITIVE LOGITS

 hendes

0.54

 epithelial

0.49

undu

0.49

 enkelte

0.47

OVERALL

0.47

 incoming

0.47

 femmin

0.46

はじめに

0.46

 behalf

0.46

 neder

0.45

Activations Density 0.690%

repeated usage of the word "the" and related structure in textual data

No Comments

No Known Activations