INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

2:0.10

3:0.09

4:0.07

5:0.07

6:0.07

7:0.07

8:0.08

9:0.09

10:0.09

11:0.06

Negative Logits

-3.03

�醒

-2.98

{:

-2.92

xual

-2.82

GG

-2.80

*)

-2.79

 triv

-2.77

oad

-2.73

emale

-2.70

Attach

-2.67

POSITIVE LOGITS

―

2.69

Sev

2.65

 Russo

2.61

 Stein

2.61

 Stephen

2.55

 vows

2.54

SEE

2.50

 stake

2.46

Mos

2.44

 Spice

2.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.