INDEX

Explanations

terms related to grammatical roles and cases in language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 itſelf

-0.94

 Anſ

-0.90

 iſt

-0.84

 Jefus

-0.82

 Majefty

-0.81

 ―――――

-0.81

 raiſ

-0.80

 myſelf

-0.80

ſelves

-0.79

 ſche

-0.78

POSITIVE LOGITS

 cardiaque

0.64

AndEndTag

0.63

 colorés

0.62

 épais

0.60

 électriques

0.59

 témoins

0.59

 dieux

0.58

IntoConstraints

0.58

featureID

0.58

 elettrico

0.57

Activations Density 0.124%

terms related to grammatical roles and cases in language

No Comments

No Known Activations