INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.7.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

1:0.07

2:0.07

3:0.08

4:0.09

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

�

-2.61

レ

-2.60

ノ

-2.32

ヤ

-2.29

ブ

-2.18

�

-2.17

ム

-2.13

オ

-2.12

イ

-2.09

shock

-2.08

POSITIVE LOGITS

 Marg

2.01

 Attempt

1.99

 presided

1.97

 Resources

1.97

 Procedures

1.90

 Scholar

1.90

 Publishers

1.88

ilit

1.88

 balk

1.86

 presupp

1.86

Activations Density 0.000%

No Known Activations

This feature has no known activations.