INDEX

Explanations

transitional phrases and introductions to background information

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

Xna

-0.66

ราะ

-0.60

 onPostExecute

-0.57

 oars

-0.55

 ISNI

-0.54

apunov

-0.54

jspx

-0.54

 ritrov

-0.54

 Tacitus

-0.53

kadot

-0.53

POSITIVE LOGITS

 sebelumnya

0.82

 Paglinawan

0.79

 zuvor

0.76

 beforehand

0.76

 préalable

0.74

 auparavant

0.73

pierw

0.67

 vorher

0.64

 previamente

0.63

 wcześniej

0.63

Activations Density 0.441%

transitional phrases and introductions to background information

No Comments

No Known Activations