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

0:0.07

1:0.07

2:0.08

3:0.08

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

sein

-2.94

archive

-2.93

azes

-2.93

agos

-2.86

rosso

-2.76

aspers

-2.75

angelo

-2.73

 -----

-2.65

 conqu

-2.64

defense

-2.61

POSITIVE LOGITS

Jaw

2.97

 Clicker

2.97

 Lamb

2.96

 Jinn

2.95

Kw

2.88

 Mulcair

2.78

~~~~

2.78

 Drone

2.76

NL

2.72

Osw

2.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.