INDEX

Explanations

expressions of comparison and degree

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 useEffect

-0.64

 Audiodateien

-0.59

ItemBackground

-0.57

 autorytatywna

-0.55

Geplaatst

-0.55

EDEFAULT

-0.54

 hesitate

-0.54

WarningLevel

-0.54

MLLoader

-0.53

 utafitiHapana

-0.53

POSITIVE LOGITS

 facie

0.58

Jegyzetek

0.55

saraba

0.53

Források

0.53

 diphtheria

0.52

Lähteet

0.52

 Falco

0.51

Ork

0.50

 recovery

0.50

 Verdi

0.50

Activations Density 0.273%

expressions of comparison and degree

No Comments

No Known Activations