INDEX

Explanations

references to various plans and planning processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

ICULO

-0.91

enderror

-0.90

NameInMap

-0.85

Hauptartikel

-0.83

 Middleware

-0.83

ISTICS

-0.80

fromCharCode

-0.80

جستارهای

-0.79

InjectAttribute

-0.79

perties

-0.77

POSITIVE LOGITS

 plan

2.25

 PLAN

2.21

plan

2.20

 Plan

2.18

 plans

2.15

Plan

2.13

PLAN

2.00

 Plans

1.97

plans

1.90

Plans

1.82

Activations Density 0.052%

references to various plans and planning processes

No Comments

No Known Activations