INDEX

Explanations

phrases indicating user instructions or requests for clarification

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

цездатний

-0.65

:✨

-0.61

 चीज़ों

-0.59

 acoper

-0.58

windowFixed

-0.57

 BoxFit

-0.54

 محفوظة

-0.53

AndEndTag

-0.52

tonode

-0.52

RenderAtEndOf

-0.52

POSITIVE LOGITS

XmlSchema

0.61

 DBNull

0.59

urbed

0.57

EditorBrowsable

0.55

diad

0.55

 Gré

0.55

$.\\

0.53

 gram

0.53

effort

0.53

AllAfrica

0.52

Activations Density 0.607%

phrases indicating user instructions or requests for clarification

No Comments

No Known Activations