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

0:0.09

1:0.09

2:0.08

3:0.09

4:0.08

5:0.08

6:0.06

7:0.06

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

MPH

-2.82

 stim

-2.79

lift

-2.65

TM

-2.52

acus

-2.49

RL

-2.44

 Swim

-2.44

.","

-2.44

 Manz

-2.43

STEM

-2.43

POSITIVE LOGITS

 republican

2.88

umbnail

2.63

reements

2.63

arij

2.61

olia

2.59

uncture

2.53

Accessory

2.50

odcast

2.48

lesiastical

2.48

inion

2.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.