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

0:0.09

1:0.07

2:0.08

3:0.09

4:0.08

5:0.09

6:0.08

7:0.07

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

CTV

-3.80

ISS

-3.12

NAS

-2.66

nr

-2.62

 Salary

-2.62

ilts

-2.55

pedia

-2.54

capacity

-2.51

WT

-2.50

 correction

-2.49

POSITIVE LOGITS

 Navajo

3.14

 Chou

2.90

 Colomb

2.87

paio

2.85

aur

2.75

chedel

2.74

hammad

2.73

CU

2.72

ulkan

2.69

quished

2.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.