INDEX

Explanations

system-related terms in the context of programming or computing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 NACIONAL

-0.72

 mijne

-0.69

 Cæsar

-0.69

Geplaatst

-0.66

 yoksa

-0.65

 HISTORIA

-0.62

 simplicité

-0.62

 quæ

-0.62

 bonté

-0.62

 naselje

-0.61

POSITIVE LOGITS

typeorm

0.66

WriteLiteral

0.66

InvalidProtocol

0.65

sys

0.64

IVEREF

0.63

GeoNames

0.62

"]).

0.61

RegressionTest

0.60

 referenties

0.59

 дописавши

0.59

Activations Density 0.233%

system-related terms in the context of programming or computing

No Comments

No Known Activations