INDEX

Explanations

references to decision-making processes

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

2:0.07

3:0.07

4:0.08

5:0.09

6:0.07

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

raq

-2.80

amped

-2.70

 Sadd

-2.67

ainment

-2.59

 Spiel

-2.54

 Mana

-2.48

pmwiki

-2.47

 Wrest

-2.46

gra

-2.44

 upro

-2.42

POSITIVE LOGITS

 Berm

3.12

bians

2.91

¶

2.65

 Malays

2.64

[[

2.61

gyn

2.52

chrom

2.51

metry

2.46

gon

2.45

philis

2.40

Activations Density 0.000%

references to decision-making processes

No Known Activations