INDEX

Explanations

conversational phrases indicating uncertainty or hesitation

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

UserScript

-0.74

Numerology

-0.70

expandindo

-0.70

DoubleQuotes

-0.70

oneph

-0.69

uxxxx

-0.66

LEncoder

-0.66

 getItemId

-0.65

 оригіналу

-0.65

httphttps

-0.64

POSITIVE LOGITS

こういう

0.46

DockStyle

0.46

 cases

0.45

arev

0.45

 gerçekten

0.44

 truly

0.44

tume

0.43

 next

0.43

确实

0.43

new

0.43

Activations Density 0.935%

conversational phrases indicating uncertainty or hesitation

No Comments

No Known Activations