INDEX

Explanations

references to specific entities or concepts, particularly names and notable objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

er

-0.92

ificance

-0.85

angered

-0.81

 Argos

-0.81

SequentialGroup

-0.77

aryen

-0.76

ER

-0.75

ergies

-0.75

ErrorListener

-0.75

XmlAccessType

-0.74

POSITIVE LOGITS

 Denn

0.77

czer

0.72

Vall

0.72

————————————————

0.71

hasNext

0.70

 cruze

0.69

hev

0.69

icator

0.67

 vrijwilli

0.67

 preventivo

0.66

Activations Density 0.873%

references to specific entities or concepts, particularly names and notable objects

No Comments

No Known Activations