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

1:0.05

2:0.08

3:0.09

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

 intermittent

-1.82

 artif

-1.78

 privile

-1.75

 resp

-1.70

 acknowled

-1.65

 extingu

-1.65

ciating

-1.64

 abnormal

-1.63

 subsequ

-1.62

 concess

-1.61

POSITIVE LOGITS

spin

1.76

 Turtles

1.70

stars

1.70

birds

1.69

perture

1.61

atoon

1.60

mobile

1.58

 moons

1.57

Ten

1.56

OTUS

1.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.