INDEX

Explanations

terms related to internal and external systems or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 McClure

-0.85

fromCharCode

-0.80

 officiellement

-0.73

 revista

-0.72

 poética

-0.71

 casado

-0.70

 vitamine

-0.70

 Montrose

-0.70

 casada

-0.70

 turístico

-0.69

POSITIVE LOGITS

 Internal

1.32

 INTERNAL

1.30

 internal

1.29

Internal

1.17

internal

1.16

ternal

1.08

INTERNAL

1.04

 internally

1.00

 Intern

0.95

 internas

0.94

Activations Density 0.126%

terms related to internal and external systems or structures

No Comments

No Known Activations