INDEX

Explanations

terms related to explosive events and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Normdatei

-0.78

 carottes

-0.60

^(

-0.60

inds

-0.60

marginHorizontal

-0.57

ScopeManager

-0.56

tslib

-0.55

ImageContext

-0.55

 Cotter

-0.54

gesehen

-0.54

POSITIVE LOGITS

 explosions

1.37

 explosion

1.32

 Explosion

1.29

 blown

1.21

 explodes

1.20

 explosive

1.19

 Explosive

1.17

 explosives

1.17

 exploding

1.14

 exploded

1.13

Activations Density 0.193%

terms related to explosive events and their consequences

No Comments

No Known Activations