INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.09

9:0.08

10:0.07

11:0.09

Negative Logits

ECB

-3.37

 mathemat

-2.98

 Mosque

-2.95

"],"

-2.87

 mathematic

-2.81

 pope

-2.77

 cryptography

-2.71

 Guardiola

-2.67

 Vatican

-2.66

Pont

-2.64

POSITIVE LOGITS

licks

3.02

obos

2.89

Season

2.57

ients

2.54

netflix

2.52

iences

2.52

 inventory

2.52

orrow

2.51

ibles

2.44

LOW

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.