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

1:0.06

2:0.09

3:0.07

4:0.07

5:0.09

6:0.09

7:0.07

8:0.07

9:0.09

10:0.08

11:0.09

Negative Logits

CLR

-2.96

 Collins

-2.94

 acid

-2.71

 Tone

-2.70

Pu

-2.48

 Moody

-2.43

-2.42

 Morton

-2.41

 King

-2.40

 Pearson

-2.38

POSITIVE LOGITS

ethical

3.06

auntlets

2.92

Mars

2.89

fing

2.86

Syria

2.72

Surv

2.67

milo

2.62

ogyn

2.62

fal

2.60

Truth

2.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.