INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

3:0.07

4:0.08

5:0.07

6:0.09

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

SPA

-1.28

CL

-1.20

SEC

-1.20

SU

-1.18

 actionGroup

-1.18

MSG

-1.18

 contributions

-1.17

 unman

-1.17

}}}

-1.16

 conditions

-1.16

POSITIVE LOGITS

gaard

1.68

rigan

1.53

pherd

1.36

woods

1.29

 bounded

1.27

undrum

1.25

rolog

1.24

plin

1.24

ijk

1.24

udic

1.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.