INDEX

Explanations

references to patterns in data or phenomena

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

PerformLayout

-0.95

CURLOPT

-0.94

 doPost

-0.89

 CURLOPT

-0.88

 íntimo

-0.88

קישורים

-0.86

outchouc

-0.85

 stål

-0.85

ilibrium

-0.84

balanceOf

-0.83

POSITIVE LOGITS

 pattern

2.45

 patterns

2.42

 Pattern

2.21

 Patterns

2.20

 PATTERN

2.13

pattern

2.08

Patterns

2.05

Pattern

2.04

patterns

1.88

PATTERN

1.67

Activations Density 0.056%

references to patterns in data or phenomena

No Comments

No Known Activations