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

0:0.10

1:0.07

2:0.09

3:0.07

4:0.08

5:0.10

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 Gillespie

-1.62

 specificity

-1.62

uras

-1.55

odium

-1.54

�

-1.49

alogue

-1.48

etics

-1.46

amba

-1.45

Torrent

-1.43

igslist

-1.40

POSITIVE LOGITS

stocks

1.91

NetMessage

1.87

 subscribing

1.76

 stocks

1.58

stock

1.57

 spons

1.51

Stock

1.51

 retiring

1.49

catentry

1.48

 stock

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.