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

1:0.09

2:0.08

3:0.07

4:0.07

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

vib

-1.69

 themed

-1.54

Dys

-1.51

Moj

-1.49

 Yosemite

-1.44

 Recomm

-1.44

Oxy

-1.43

 Glow

-1.43

 Vegas

-1.40

 Grav

-1.38

POSITIVE LOGITS

REP

1.73

heet

1.51

itiveness

1.47

peak

1.47

lain

1.46

PUT

1.45

nces

1.44

ince

1.42

alion

1.42

Climate

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.