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

1:0.08

2:0.07

3:0.07

4:0.08

5:0.08

6:0.09

7:0.09

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 predictor

-2.97

mist

-2.84

etheless

-2.80

caster

-2.71

.#

-2.71

asher

-2.63

 fixture

-2.59

bots

-2.55

tackle

-2.47

 relentlessly

-2.42

POSITIVE LOGITS

Kou

3.45

Cer

3.16

Pap

3.06

 Piet

3.04

Xer

2.95

Kaw

2.91

 Nike

2.86

 Prot

2.68

Kru

2.64

Cyr

2.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.