INDEX

Explanations

references to mathematical variables and kernel concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

smo

-0.57

smooth

-0.57

gerald

-0.55

 Unwin

-0.55

agreb

-0.54

 smooth

-0.53

пія

-0.53

 familiar

-0.53

 Smooth

-0.52

oczes

-0.51

POSITIVE LOGITS

assium

1.12

 متعلقه

1.06

 GlobalKey

1.05

KP

1.04

 >=",

0.99

 Kepler

0.96

principalColumn

0.95

Ks

0.95

 Kenner

0.95

sī

0.95

Activations Density 0.919%

references to mathematical variables and kernel concepts

No Comments

No Known Activations