INDEX

Explanations

code-related structures or operations

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

Tokens within square brackets

np_acts-logits-general · gemini-2.0-flash

empty

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

KommentareTeilen

-0.67

 kasarigan

-0.52

Buildable

-0.51

★★★★☆

-0.51

 sombra

-0.50

Vidite

-0.49

 vedette

-0.48

 trống

-0.48

 ménages

-0.48

anément

-0.48

POSITIVE LOGITS

principalColumn

0.74

 Anſ

0.69

 Houſe

0.67

VolleyError

0.67

neſs

0.67

0.65

RectangleBorder

0.65

存于互联网档案馆

0.64

0.63

MemoryWarning

0.61

Activations Density 0.387%

code-related structures or operations

Tokens within square brackets

empty

No Comments

No Known Activations