INDEX

Explanations

terms related to the execution of processes or actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MessageTagHelper

-0.95

 mapStateToProps

-0.85

NTB

-0.84

Daf

-0.82

MigrationBuilder

-0.80

évaluateur

-0.79

 Sarm

-0.78

########.

-0.77

bieter

-0.77

ALR

-0.77

POSITIVE LOGITS

 Execution

1.22

 execution

1.21

 EXEC

1.20

 Executes

1.11

EXEC

1.10

 Execute

1.09

 execute

1.08

execu

1.06

 executions

1.05

exec

1.05

Activations Density 0.057%

terms related to the execution of processes or actions

No Comments

No Known Activations