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

2:0.07

3:0.07

4:0.08

5:0.08

6:0.08

7:0.09

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

 SHAR

-2.85

TS

-2.65

rence

-2.55

SY

-2.53

ENTS

-2.46

raits

-2.45

Riy

-2.40

="#

-2.36

Bloomberg

-2.36

nces

-2.34

POSITIVE LOGITS

 condom

3.06

 Commando

2.90

]]

2.88

 mate

2.78

 submar

2.69

 dolphin

2.62

ocom

2.53

 cardio

2.52

 condoms

2.48

 Polo

2.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.