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

0:0.07

1:0.07

2:0.08

3:0.08

4:0.09

5:0.09

6:0.09

7:0.08

8:0.08

9:0.07

10:0.06

11:0.08

Negative Logits

 Canaveral

-1.69

ーテ

-1.59

 Partial

-1.54

 Celt

-1.52

 sugg

-1.51

ylon

-1.50

 Commerce

-1.50

 Booker

-1.50

��

-1.49

Byz

-1.48

POSITIVE LOGITS

organized

1.69

ently

1.68

stable

1.54

affiliated

1.53

sum

1.53

backed

1.51

where

1.51

kill

1.49

inally

1.49

interstitial

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.