INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

1:0.06

2:0.09

3:0.09

4:0.10

5:0.08

6:0.08

7:0.09

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

POL

-1.73

�

-1.62

Brand

-1.58

});

-1.51

External

-1.50

 airing

-1.50

available

-1.46

delay

-1.45

 reinforcing

-1.43

�

-1.43

POSITIVE LOGITS

 kingdoms

1.98

 Amen

1.90

 Bulgar

1.77

inav

1.74

perors

1.66

 empires

1.66

 Tycoon

1.65

lasses

1.65

iuses

1.64

 Aram

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.