INDEX

Explanations

phrases related to problem-solving and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Storia

-0.66

ywna

-0.65

 mijne

-0.64

manteau

-0.62

 Cæsar

-0.61

IsPostBack

-0.61

 Roskov

-0.61

ьаж

-0.61

jalá

-0.60

AddTagHelper

-0.59

POSITIVE LOGITS

 figure

4.66

figure

4.05

 figures

3.72

figures

3.32

 Figure

3.14

 FIGURE

3.01

 Figures

2.95

 figura

2.94

 figured

2.90

Figure

2.85

Activations Density 0.147%

phrases related to problem-solving and understanding

No Comments

No Known Activations