INDEX

Explanations

technical terms and specifications related to GPU architecture and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Swe

-0.63

Slu

-0.62

OwnerId

-0.61

########.

-0.61

 auri

-0.59

ünd

-0.59

 Kuli

-0.57

ghi

-0.56

öh

-0.55

 SPDX

-0.55

POSITIVE LOGITS

complexContent

0.78

reactivex

0.75

 Meksiku

0.69

 المعيارى

0.68

WritableDatabase

0.68

ConstraintMaker

0.65

 again

0.64

setVerticalGroup

0.60

 nuevamente

0.59

 typelib

0.59

Activations Density 0.336%

technical terms and specifications related to GPU architecture and performance metrics

No Comments

No Known Activations