INDEX

Explanations

text related to traumatic events and survival stories

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.15

1:0.07

2:0.05

3:0.05

4:0.05

5:0.04

6:0.10

7:0.07

8:0.02

9:0.05

10:0.25

11:0.06

Negative Logits

Weiss

-3.27

 Lann

-3.22

 Thrones

-3.06

 Weiss

-3.00

aeper

-2.77

inery

-2.74

otation

-2.69

 Staten

-2.69

 Sparrow

-2.66

Tr

-2.65

POSITIVE LOGITS

Kab

9.99

Zub

5.36

Kad

4.99

Kub

4.41

Ez

4.29

Kam

4.26

Zak

4.23

Kap

4.14

Jal

4.14

Naj

4.12

Activations Density 0.003%

text related to traumatic events and survival stories

No Comments

No Known Activations