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

0:0.09

1:0.08

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.06

9:0.07

10:0.08

11:0.08

Negative Logits

 disposable

-3.15

 twent

-2.90

 hoard

-2.88

wage

-2.82

dest

-2.81

ucket

-2.78

ulk

-2.77

wives

-2.73

adish

-2.72

 welf

-2.69

POSITIVE LOGITS

 Cardinal

3.60

 partName

3.07

 Cardinals

2.99

PCB

2.94

 Presence

2.89

 NVIDIA

2.87

OTA

2.86

 Genius

2.74

Oracle

2.73

 Chips

2.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.