INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.09

2:0.09

3:0.07

4:0.07

5:0.08

6:0.08

7:0.08

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

 Honour

-1.45

 Wrest

-1.38

onto

-1.32

 punched

-1.32

 Slot

-1.31

Sgt

-1.31

 tender

-1.29

Marginal

-1.29

birds

-1.27

 Detective

-1.27

POSITIVE LOGITS

amsung

1.88

omsky

1.61

utterstock

1.59

inav

1.55

 millenn

1.54

igmatic

1.53

umann

1.51

osponsors

1.48

 intensify

1.48

ahime

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.