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

Head Attr Weights

0:0.08

1:0.09

2:0.09

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.09

9:0.06

10:0.08

11:0.08

Negative Logits

 Loki

-1.88

abal

-1.73

 APPLIC

-1.67

 Artemis

-1.58

Aph

-1.58

Skin

-1.58

sung

-1.57

Shy

-1.56

Suk

-1.56

 Surviv

-1.55

POSITIVE LOGITS

eon

1.79

artment

1.61

hett

1.47

rely

1.44

illet

1.42

reply

1.42

rily

1.41

iably

1.41

nington

1.37

 unused

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.