INDEX

Explanations

terms related to "tor" or "toric" variations in different contexts

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

ending in "tor" or "Tor"

np_acts-logits-general · gemini-2.0-flash

tortious, toric, torrefaction, torsional

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Matter

-0.61

Filmografia

-0.61

彡

-0.59

audiovisuel

-0.58

 grade

-0.58

 fact

-0.57

OMBIA

-0.56

 bisect

-0.56

 encourag

-0.56

GEBURTS

-0.55

POSITIVE LOGITS

Tor

0.88

Tor

0.83

TOR

0.82

tor

0.81

tor

0.70

HandlerContext

0.67

 createSlice

0.61

sizeCache

0.61

UnusedPrivate

0.59

TOR

0.58

Activations Density 0.085%

terms related to "tor" or "toric" variations in different contexts

ending in "tor" or "Tor"

tortious, toric, torrefaction, torsional

No Comments

No Known Activations