INDEX

Explanations

references to long-term effects or outcomes 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 @ 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

يميديا

-0.75

createServer

-0.73

subplot

-0.70

Geplaatst

-0.67

WarningLevel

-0.65

IUrlHelper

-0.63

 UnityEditor

-0.63

Aktualisiert

-0.62

 Seeder

-0.61

Дереккөздер

-0.60

POSITIVE LOGITS

 long

4.43

long

4.08

 LONG

3.71

Long

3.71

 Long

3.64

LONG

3.49

 longer

2.89

 longue

2.87

 longest

2.82

 longa

2.76

Activations Density 0.065%

references to long-term effects or outcomes in various contexts

No Comments

No Known Activations