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

1:0.08

2:0.08

3:0.09

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

sels

-3.08

¨

-2.92

illes

-2.55

ilial

-2.48

minist

-2.47

sel

-2.44

izabeth

-2.42

��

-2.42

userc

-2.40

 phyl

-2.38

POSITIVE LOGITS

 credited

2.56

 specified

2.42

 GoPro

2.29

 said

2.25

 Ammunition

2.25

SUP

2.17

arton

2.15

HF

2.13

 recommended

2.13

blu

2.12

Activations Density 0.000%

No Known Activations

This feature has no known activations.