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

3:0.08

4:0.09

5:0.09

6:0.08

7:0.06

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

isSpecialOrderable

-3.20

�

-3.15

quished

-3.10

caps

-3.00

 Neph

-2.77

ル

-2.74

bath

-2.74

ubis

-2.68

 Seraph

-2.68

Sword

-2.68

POSITIVE LOGITS

 collaborator

2.93

 formulation

2.82

 tune

2.61

 patiently

2.60

 Rove

2.53

eton

2.51

 radio

2.51

 tailor

2.51

 unanim

2.50

 collaborators

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.