INDEX

Explanations

elements related to requirements and optional features in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 AssemblyProduct

-0.78

PerformLayout

-0.75

]<<"

-0.74

 AssemblyCompany

-0.74

CodeAttribute

-0.73

TypedDataSet

-0.72

IVEREF

-0.72

脚注の使い方

-0.71

abestanden

-0.71

 Roskov

-0.71

POSITIVE LOGITS

 optional

2.70

optional

2.27

 Optional

2.25

Optional

2.24

 OPTIONAL

2.00

OPTIONAL

1.94

 opcional

1.89

 optionally

1.80

 voluntary

1.69

 Option

1.59

Activations Density 0.408%

elements related to requirements and optional features in various contexts

No Comments

No Known Activations