INDEX

Explanations

sections or discussions pertaining to features of products or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jsonwebtoken

-0.54

 mijne

-0.54

 للمعارف

-0.53

unsplash

-0.52

 IFTT

-0.51

 endIndex

-0.49

تقاوى

-0.48

Personensuche

-0.47

Архівовано

-0.47

orElseThrow

-0.47

POSITIVE LOGITS

 features

1.02

 Features

1.02

features

0.93

Features

0.93

 FEATURES

0.87

FEATURES

0.82

 feature

0.79

特点

0.77

feature

0.76

 Feature

0.75

Activations Density 0.004%

sections or discussions pertaining to features of products or entities

No Comments

No Known Activations