INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.08

4:0.09

5:0.06

6:0.08

7:0.09

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

Tube

-1.55

 Blueprint

-1.43

[|

-1.43

 GOODMAN

-1.42

FX

-1.41

[/

-1.34

Craft

-1.34

Ultimate

-1.32

 Debug

-1.31

Premium

-1.30

POSITIVE LOGITS

 pardon

1.38

 homosexual

1.38

 acquaintance

1.35

 divorced

1.34

married

1.34

���

1.34

 interpreter

1.34

 habit

1.34

 informant

1.33

 vener

1.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.