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

0:0.08

1:0.08

2:0.08

3:0.07

4:0.09

5:0.08

6:0.07

7:0.08

8:0.07

9:0.09

10:0.08

11:0.07

Negative Logits

 Saud

-2.75

Maw

-2.71

 Dawson

-2.66

 Fairfax

-2.57

Sham

-2.56

 Aman

-2.54

Wan

-2.50

 Carlson

-2.50

owicz

-2.49

 Nicarag

-2.49

POSITIVE LOGITS

mediate

3.03

oreal

2.58

illy

2.55

itte

2.53

cffffcc

2.51

 leagues

2.51

 bounce

2.45

 hills

2.42

rank

2.41

oor

2.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.