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

3:0.07

4:0.08

5:0.09

6:0.07

7:0.07

8:0.07

9:0.09

10:0.09

11:0.08

Negative Logits

Ng

-2.72

 faked

-2.69

Dash

-2.69

Georg

-2.63

 Emin

-2.59

Street

-2.56

Fu

-2.56

 Mechdragon

-2.52

Samsung

-2.48

 stunt

-2.48

POSITIVE LOGITS

ritic

3.01

teenth

2.82

 youngest

2.79

iott

2.66

orest

2.55

arten

2.55

veyard

2.55

cy

2.51

Sly

2.50

ichever

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.