INDEX

Explanations

phrases indicating completion or finalization of tasks or processes

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

Nicky

-0.72

mux

-0.69

pym

-0.66

 Anfitrión

-0.66

 diken

-0.66

fontsize

-0.65

ongiorno

-0.65

nicze

-0.65

 heapq

-0.64

 Rupert

-0.63

POSITIVE LOGITS

 completed

1.49

completed

1.39

 Comple

1.33

 comple

1.32

 completion

1.29

 finished

1.28

 completing

1.21

 completes

1.21

Completed

1.20

 complete

1.17

Activations Density 0.099%

phrases indicating completion or finalization of tasks or processes

No Comments

No Known Activations