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

4:0.07

5:0.08

6:0.08

7:0.09

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

 seiz

-2.03

fficiency

-1.88

 cull

-1.83

 destro

-1.77

Lei

-1.76

 leakage

-1.75

 basics

-1.74

 differently

-1.70

 tatt

-1.70

enko

-1.68

POSITIVE LOGITS

Media

1.95

osponsors

1.83

mc

1.71

Laura

1.69

�

1.68

inally

1.68

Touch

1.66

else

1.63

Mac

1.62

Dem

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.