INDEX

Explanations

programming and technical terms related to software components and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

-1.16

-1.09

-1.06

in

-1.00

-0.98

-0.94

on

-0.93

and

-0.91

-0.88

POSITIVE LOGITS

 ſind

1.68

 ་་

1.67

 photolibrary

1.67

Efq

1.62

 Houſe

1.61

 ―――――

1.59

хьтан

1.59

 itſelf

1.54

 Majefty

1.51

 Anſ

1.51

Activations Density 0.603%

programming and technical terms related to software components and functions

No Comments

No Known Activations