INDEX

Explanations

sentences that express uncertainty or ask questions

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

ArrowToggle

-0.85

 فريبيس

-0.82

 المعيارى

-0.75

ThroughAttribute

-0.75

webElement

-0.68

<bos>

-0.68

AddTagHelper

-0.65

ScopeManager

-0.62

contentLoaded

-0.60

InputTagHelper

-0.59

POSITIVE LOGITS

0.53

Bronnen

0.53

openzeppelin

0.53

räume

0.52

Gön

0.52

 Heilig

0.51

purpose

0.47

 المكتبه

0.47

Rapport

0.47

 Thorne

0.46

Activations Density 0.655%

sentences that express uncertainty or ask questions

No Comments

No Known Activations