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

0:0.08

1:0.08

2:0.08

3:0.08

4:0.09

5:0.07

6:0.08

7:0.09

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

 AIDS

-2.80

 homelessness

-2.78

 loneliness

-2.69

Ou

-2.69

 interpersonal

-2.63

 anecdotal

-2.62

ifference

-2.58

 homeless

-2.56

 baskets

-2.53

 respondent

-2.50

POSITIVE LOGITS

 Tune

2.92

 Enhance

2.80

Corn

2.76

Rex

2.72

 Dust

2.64

eryl

2.63

 Bahrain

2.63

 Matte

2.59

uador

2.59

 Leon

2.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.