INDEX

Explanations

elements related to coding and technical specifications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Nemo

-0.49

npr

-0.45

trui

-0.44

gerufen

-0.44

Poppins

-0.42

 tito

-0.41

 swim

-0.41

loem

-0.41

bobox

-0.40

isim

-0.40

POSITIVE LOGITS

 IBOutlet

0.79

IBOutlet

0.72

UnusedPrivate

0.69

Autoritní

0.68

antlr

0.67

 Paglinawan

0.67

жнему

0.66

bukkit

0.66

__(/*!

0.65

 <<<<<<<<<<<<<<

0.64

Activations Density 0.026%

elements related to coding and technical specifications

No Comments

No Known Activations