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

0:0.08

1:0.05

2:0.09

3:0.07

4:0.08

5:0.07

6:0.08

7:0.07

8:0.09

9:0.07

10:0.10

11:0.09

Negative Logits

д

-2.02

ebook

-1.88

Sov

-1.72

м

-1.67

-1.65

 Lans

-1.62

MJ

-1.62

 Hels

-1.61

nep

-1.61

[/

-1.56

POSITIVE LOGITS

ashington

2.09

 measuring

1.77

 debating

1.77

 champions

1.72

 overlooking

1.63

 defining

1.58

 democracies

1.58

ideon

1.57

 empir

1.57

 graded

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.