INDEX

Explanations

terms related to research methodologies and statistical analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

mobileqq

-0.65

ExecuteReader

-0.59

 spille

-0.53

writerow

-0.52

 szen

-0.49

 Physica

-0.49

îtra

-0.49

mampuan

-0.48

endcsname

-0.47

seiti

-0.46

POSITIVE LOGITS

 ―――――

0.55

Glass

0.55

 Forumite

0.55

 Método

0.54

 WAVE

0.53

CodeAttribute

0.53

Tril

0.53

WebControls

0.53

 Meto

0.53

 Wave

0.53

Activations Density 0.326%

terms related to research methodologies and statistical analysis

No Comments

No Known Activations