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

1:0.05

2:0.09

3:0.07

4:0.08

5:0.09

6:0.07

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

 Rabbi

-1.83

 Presbyter

-1.81

 Chero

-1.76

 Zhou

-1.72

 mathemat

-1.67

 Phar

-1.66

odge

-1.66

 congr

-1.63

 Chrysler

-1.61

terday

-1.61

POSITIVE LOGITS

aeda

1.90

pod

1.85

venge

1.67

idad

1.63

amaru

1.63

aclysm

1.60

complex

1.59

idal

1.56

host

1.56

emonic

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.