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

0:0.07

1:0.08

2:0.06

3:0.08

4:0.08

5:0.09

6:0.08

7:0.07

8:0.08

9:0.08

10:0.10

11:0.07

Negative Logits

 renamed

-2.12

escription

-1.98

 drafting

-1.95

][

-1.92

\"

-1.92

\'

-1.87

 payout

-1.82

ablish

-1.81

 broadcasting

-1.81

¯

-1.81

POSITIVE LOGITS

Pocket

2.30

黒

2.09

Ub

2.08

Oracle

2.05

vag

2.02

Questions

1.96

 Rohingya

1.94

Beast

1.93

google

1.91

Gh

1.86

Activations Density 0.000%

No Known Activations

This feature has no known activations.