INDEX

Explanations

references to specific classes or categories in various contexts

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

The token "class"

np_acts-logits-general · gemini-2.0-flash

class

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

AndEndTag

-0.65

 aceptas

-0.60

webElementXpaths

-0.55

familien

-0.55

🏿

-0.54

ubernur

-0.53

Phases

-0.51

🏽

-0.50

लग

-0.50

 légales

-0.50

POSITIVE LOGITS

rooms

0.89

ically

0.89

ROOM

0.76

CastException

0.72

sieke

0.71

mates

0.67

ics

0.63

ROOMS

0.62

fication

0.60

mate

0.60

Activations Density 0.111%

references to specific classes or categories in various contexts

The token "class"

class

No Comments

No Known Activations