INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

1:0.06

2:0.09

3:0.07

4:0.07

5:0.08

6:0.08

7:0.08

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

Bav

-3.23

 Okinawa

-2.94

 Munich

-2.91

Mü

-2.74

 Bundes

-2.71

 Germany

-2.71

 Reconstruction

-2.68

PCB

-2.66

 genomes

-2.59

 americ

-2.58

POSITIVE LOGITS

cffffcc

3.40

olicited

3.06

caster

3.02

 Mistress

2.99

Rogue

2.83

emouth

2.77

sword

2.76

Bright

2.72

redd

2.71

shine

2.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.