INDEX

Explanations

references to specific scientific terms and variable names related to data analysis or experimentation

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

 AssemblyCompany

-0.81

voorbeeld

-0.70

ddha

-0.67

endregion

-0.64

-0.63

ntgen

-0.62

moveToFirst

-0.62

iedene

-0.62

DebuggerNonUser

-0.62

consulté

-0.60

POSITIVE LOGITS

Jop

1.13

FAP

1.12

pable

1.10

bop

1.06

Bop

1.05

cip

1.04

Jep

1.03

Wap

1.03

Cip

0.98

Mop

0.98

Activations Density 0.967%

references to specific scientific terms and variable names related to data analysis or experimentation

No Comments

No Known Activations