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

1:0.06

2:0.09

3:0.08

4:0.07

5:0.09

6:0.07

7:0.09

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

artifacts

-1.86

-1.69

 Provided

-1.66

gren

-1.55

qqa

-1.54

 Shogun

-1.49

 indo

-1.49

amo

-1.47

ruction

-1.45

artisan

-1.45

POSITIVE LOGITS

DonaldTrump

1.80

GBT

1.67

 Carey

1.54

.",

1.53

istar

1.52

atalie

1.51

WATCH

1.50

Osw

1.46

`.

1.45

 neurological

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.