INDEX

Explanations

references to events and consequences

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

events "happening" or "occurring"

np_acts-logits-general · gemini-2.0-flash

things happening

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

"],

-0.59

-0.57

äuser

-0.55

WithIOException

-0.53

yson

-0.52

@}

-0.52

 intptr

-0.51

".

-0.51

 Paix

-0.51

orang

-0.50

POSITIVE LOGITS

 happen

1.54

 happened

1.49

 happening

1.47

 occur

1.41

 happens

1.36

 occurs

1.32

 occurred

1.29

happened

1.24

 occurring

1.22

 Occur

1.21

Activations Density 0.422%

references to events and consequences

events "happening" or "occurring"

things happening

No Comments

No Known Activations