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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.06

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

enfranch

-3.25

 Morsi

-2.90

peed

-2.75

milo

-2.73

endi

-2.70

 Quadro

-2.69

amon

-2.68

cius

-2.66

 Nvidia

-2.64

GPU

-2.61

POSITIVE LOGITS

 Lindsay

2.77

vill

2.77

 Gilmore

2.71

 Scarborough

2.69

 Nurse

2.61

 grate

2.51

 Sailor

2.50

 ANGEL

2.44

 trio

2.41

 Courtney

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.