INDEX

Explanations

structured numerical data, likely for coding or identification purposes

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

Number followed by parentheses

np_acts-logits-general · gemini-2.0-flash

numbers and codes

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

 CYTHON

-0.90

 StatefulWidget

-0.73

WriteAttribute

-0.71

 serializers

-0.69

uteria

-0.68

Ferdin

-0.67

 Shelly

-0.66

orothy

-0.66

 nahilalakip

-0.66

 Corbett

-0.65

POSITIVE LOGITS

initialValue

0.61

 vache

0.60

ondissement

0.59

 Huguen

0.58

AndEndTag

0.58

JSONException

0.58

UNRELATED

0.58

RunAsync

0.58

th

0.56

 jakarta

0.55

Activations Density 0.678%

structured numerical data, likely for coding or identification purposes

Number followed by parentheses

numbers and codes

No Comments

No Known Activations