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

1:0.07

2:0.08

3:0.09

4:0.07

5:0.08

6:0.08

7:0.08

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

irs

-1.85

rils

-1.80

enes

-1.78

orable

-1.78

nings

-1.73

abase

-1.71

ench

-1.71

andr

-1.69

ulum

-1.69

orget

-1.68

POSITIVE LOGITS

 advising

2.07

 conscientious

1.87

 shorthand

1.83

 suffice

1.78

 pacif

1.76

 Disability

1.74

 apologies

1.73

+=

1.72

 advis

1.72

 defer

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.