INDEX

Explanations

references to portraits and photography

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 cervello

-0.70

 resourceCulture

-0.65

DATABASES

-0.64

)|^{

-0.62

wsz

-0.61

 dataSnapshot

-0.61

frig

-0.61

ợn

-0.60

 shears

-0.60

 žád

-0.59

POSITIVE LOGITS

 portrait

0.97

 PORTRAIT

0.95

 Portrait

0.90

Portrait

0.84

curricular

0.82

portrait

0.82

Curriculum

0.81

 portraits

0.80

 Curriculum

0.79

IBOutlet

0.79

Activations Density 0.483%

references to portraits and photography

No Comments

No Known Activations