INDEX

Explanations

references to specific individuals and their affiliations in academic or research contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Caruso

-0.85

ion

-0.84

ions

-0.83

pij

-0.80

Tore

-0.78

ViewFeatures

-0.77

-0.76

 Mooney

-0.75

 ANTON

-0.75

POSITIVE LOGITS

UIS

0.96

orescent

0.86

haustible

0.84

RUnlock

0.84

DockStyle

0.84

ixante

0.83

CCT

0.82

MER

0.82

uchter

0.81

 Meridian

0.81

Activations Density 2.120%

references to specific individuals and their affiliations in academic or research contexts

No Comments

No Known Activations