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

2:0.09

3:0.08

4:0.08

5:0.09

6:0.07

7:0.07

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

NetMessage

-3.86

Dash

-3.09

ommel

-3.01

emp

-2.94

marked

-2.84

dain

-2.82

Tur

-2.80

 Bagg

-2.80

Mac

-2.75

Alias

-2.71

POSITIVE LOGITS

tox

3.10

 anth

2.72

 replication

2.63

 untold

2.62

 collagen

2.61

 coll

2.59

 damn

2.54

assic

2.54

 Unreal

2.53

 goddamn

2.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.