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

1:0.07

2:0.07

3:0.07

4:0.07

5:0.07

6:0.10

7:0.09

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

�

-3.68

Maria

-3.23

 Marqu

-3.14

aukee

-3.12

 Athletic

-3.01

reau

-2.99

EMA

-2.99

ause

-2.99

ctive

-2.98

Duc

-2.94

POSITIVE LOGITS

 sailors

3.04

 stray

3.00

 tides

2.97

 spies

2.97

SEA

2.93

 slices

2.88

 rats

2.82

 birds

2.81

 satellites

2.81

 thefts

2.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.