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

0:0.08

1:0.07

2:0.07

3:0.09

4:0.09

5:0.07

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

antis

-2.31

apest

-2.02

enes

-2.01

utan

-2.01

rompt

-1.93

gow

-1.89

orst

-1.86

edom

-1.83

leeve

-1.82

okemon

-1.80

POSITIVE LOGITS

BuyableInstoreAndOnline

2.00

 digs

1.72

 Resp

1.71

 slot

1.69

 viewing

1.68

 focusing

1.65

 refurb

1.61

 athlet

1.60

 stub

1.58

 embr

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.