INDEX

Explanations

references to academic titles and roles, particularly "Professor."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

UrlResolution

-0.66

eadilan

-0.59

XtraReports

-0.56

UnusedPrivate

-0.55

 calculées

-0.54

Obrázky

-0.54

XMLSchema

-0.52

LookAnd

-0.51

INGHAM

-0.50

 zodia

-0.50

POSITIVE LOGITS

 Professor

4.00

 professor

3.99

Professor

3.79

professor

3.39

 PROFESSOR

3.33

 professors

3.33

 Professors

3.19

 Prof

2.86

Prof

2.68

Profess

2.65

Activations Density 0.054%

references to academic titles and roles, particularly "Professor."

No Comments

No Known Activations