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

2:0.08

3:0.09

4:0.08

5:0.06

6:0.08

7:0.08

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

 remod

-2.72

 McDonnell

-2.71

Koh

-2.71

 microscopic

-2.67

 retrie

-2.60

 resemb

-2.53

 rese

-2.51

 cowork

-2.51

 hawk

-2.48

 phenotype

-2.47

POSITIVE LOGITS

afe

3.12

aredevil

2.88

fb

2.87

acons

2.86

icc

2.82

cb

2.76

eca

2.71

aves

2.70

eous

2.70

llers

2.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.