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

1:0.05

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.09

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

ndra

-1.86

omore

-1.83

acia

-1.74

avia

-1.71

redo

-1.69

ogn

-1.67

annot

-1.66

ever

-1.66

ngth

-1.62

ither

-1.61

POSITIVE LOGITS

闘

1.64

龍

1.63

 FUCK

1.60

 sidx

1.60

Zup

1.55

 pounding

1.53

 deck

1.52

 guns

1.50

OV

1.48

 priests

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.