INDEX

Explanations

references to electric and electrical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Personensuche

-1.45

setVerticalGroup

-1.16

 AssemblyCulture

-1.08

 GeoNames

-1.08

 виправивши

-1.06

VIAF

-0.99

 noDo

-0.99

umoj

-0.99

 NSCoder

-0.98

glades

-0.98

POSITIVE LOGITS

 electric

2.04

 Electric

2.02

Electric

1.92

electric

1.84

 ELECTRIC

1.73

ELECTRIC

1.62

 elektr

1.46

 electrical

1.30

 Elect

1.26

电

1.25

Activations Density 0.079%

references to electric and electrical concepts

No Comments

No Known Activations