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

1:0.06

2:0.09

3:0.09

4:0.08

5:0.08

6:0.09

7:0.09

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 Slaughter

-1.77

 Bastard

-1.75

Magn

-1.68

Mut

-1.66

Script

-1.61

 Targ

-1.57

Dra

-1.50

Enh

-1.49

 Mutant

-1.48

Hun

-1.48

POSITIVE LOGITS

 certify

1.90

 reassure

1.71

 congratulated

1.67

 cryptocurrencies

1.66

thereum

1.66

rists

1.64

realDonaldTrump

1.61

aukee

1.59

merce

1.58

earchers

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.