INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.06

11:0.09

Negative Logits

court

-1.38

lesh

-1.33

 clot

-1.30

ylum

-1.30

 Asylum

-1.29

exist

-1.29

lot

-1.27

drive

-1.25

 intervene

-1.24

eur

-1.24

POSITIVE LOGITS

ongo

1.59

 Comparison

1.57

 correlations

1.50

 variability

1.46

 shading

1.46

 languages

1.46

argon

1.45

 Angle

1.45

ERC

1.39

 phylogen

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.