INDEX

Explanations

references to procedures or conditions related to medical treatments and their outcomes

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

Occurrences with time or repetition

np_acts-logits-general · gemini-2.0-flash

each time

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

SequentialGroup

-0.76

principalColumn

-0.67

getMinutes

-0.61

PropertyChanging

-0.59

 newBuilder

-0.55

 kaynağından

-0.53

Архівовано

-0.53

>--}}

-0.53

Pranala

-0.53

StrictMode

-0.53

POSITIVE LOGITS

 each

1.39

每次

1.25

 jeweils

1.25

每一次

1.22

毎回

1.13

たびに

1.09

each

1.08

 Each

1.01

 vždy

1.01

Each

0.99

Activations Density 0.889%

references to procedures or conditions related to medical treatments and their outcomes

Occurrences with time or repetition

each time

No Comments

No Known Activations