INDEX

Explanations

references to academic titles and positions held by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Besoin

-0.90

 Rite

-0.85

 Offisielt

-0.80

 skippy

-0.78

 Thiết

-0.78

 Souhaitez

-0.77

 Skyl

-0.76

ChildScrollView

-0.75

 ſche

-0.72

hintText

-0.72

POSITIVE LOGITS

 professor

1.97

 Professor

1.89

 professors

1.84

Professor

1.70

 Professors

1.70

professor

1.61

 PROFESSOR

1.53

 Prof

1.47

Profess

1.39

Prof

1.32

Activations Density 0.065%

references to academic titles and positions held by individuals

No Comments

No Known Activations