INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.11

2:0.07

3:0.08

4:0.07

5:0.08

6:0.07

7:0.07

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

Zot

-1.78

Problem

-1.74

Attempt

-1.72

enum

-1.67

 Dimension

-1.62

Ur

-1.56

�

-1.55

 Dmitry

-1.55

EEE

-1.51

 Zimbabwe

-1.51

POSITIVE LOGITS

gaard

1.73

 shoulders

1.68

seys

1.67

aunders

1.67

 shoulder

1.58

 disproportionately

1.58

 uniquely

1.57

 Creed

1.55

icent

1.54

sole

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.