INDEX

Explanations

terms and concepts associated with administrative roles and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Nostra

-0.72

olella

-0.70

HTT

-0.70

 arousal

-0.68

TacToe

-0.67

 pick

-0.66

 suitors

-0.66

 Fury

-0.66

Jor

-0.64

itattu

-0.64

POSITIVE LOGITS

ModelAdmin

1.23

 administration

1.23

 administrators

1.17

 administrations

1.16

 Administ

1.15

 Administration

1.14

administ

1.13

 Admin

1.07

administration

1.07

ADMIN

1.07

Activations Density 0.045%

terms and concepts associated with administrative roles and structures

No Comments

No Known Activations