INDEX

Explanations

descriptions of how well things match or align with particular criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 שוליים

-0.86

 تضيفلها

-0.81

 الحره

-0.81

انجليز

-0.79

Efq

-0.78

المشاركات

-0.78

 Shaksp

-0.76

cagon

-0.76

ρίς

-0.73

uksessa

-0.73

POSITIVE LOGITS

 snug

0.77

Fits

0.73

 Fits

0.69

 fits

0.64

fits

0.63

 Fitz

0.56

fit

0.55

 into

0.54

FIT

0.54

fitting

0.54

Activations Density 0.081%

descriptions of how well things match or align with particular criteria

No Comments

No Known Activations