INDEX

Explanations

references to actions taken within a legal or formal context

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

AutoField

-0.70

 للاسماء

-0.70

)++;

-0.69

(!__

-0.68

CardHeader

-0.67

 AssemblyProduct

-0.64

expandindo

-0.62

にほんブログ村

-0.61

jspx

-0.60

Copia

-0.60

POSITIVE LOGITS

 Action

0.88

 balances

0.88

 action

0.86

 actions

0.84

 balancing

0.82

Action

0.81

 Actions

0.79

 balanced

0.79

 adjustment

0.77

Actions

0.75

Activations Density 0.171%

references to actions taken within a legal or formal context

No Comments

No Known Activations