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

0:0.07

1:0.09

2:0.08

3:0.08

4:0.09

5:0.07

6:0.09

7:0.08

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

AIDS

-3.25

hate

-2.84

African

-2.70

 dermat

-2.69

jri

-2.63

 NAACP

-2.62

 Trayvon

-2.62

iannopoulos

-2.57

NBA

-2.56

HA

-2.54

POSITIVE LOGITS

stract

2.82

 reader

2.42

dq

2.41

 Quart

2.41

う

2.41

ulla

2.37

 Table

2.37

rison

2.35

Zup

2.33

\/\/

2.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.