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

0:0.07

1:0.08

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

anwhile

-2.85

rosso

-2.78

endas

-2.75

uese

-2.67

Sov

-2.64

avez

-2.62

merce

-2.57

rals

-2.53

 declass

-2.51

 Recover

-2.43

POSITIVE LOGITS

GB

2.98

 Boyle

2.97

 Rider

2.79

 Hearthstone

2.75

 Celsius

2.74

QC

2.62

PG

2.61

 Magicka

2.58

BDS

2.55

 Crescent

2.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.