INDEX

Explanations

references to patterns or pattern recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

PerformLayout

-1.02

 íntimo

-0.89

CURLOPT

-0.89

קישורים

-0.86

DotNetBar

-0.84

 CURLOPT

-0.83

ilibrium

-0.83

 doGet

-0.82

 doPost

-0.81

ajiban

-0.81

POSITIVE LOGITS

 pattern

2.62

 patterns

2.54

 Pattern

2.38

 Patterns

2.35

 PATTERN

2.29

pattern

2.26

Pattern

2.22

Patterns

2.19

patterns

2.00

PATTERN

1.77

Activations Density 0.053%

references to patterns or pattern recognition

No Comments

No Known Activations