INDEX

Explanations

names of notable individuals, particularly those with the first name "Samuel."

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_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

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.02

2:0.04

3:0.04

4:0.03

5:0.03

6:0.36

7:0.23

8:0.02

9:0.03

10:0.07

11:0.04

Negative Logits

edly

-1.61

tumblr

-1.46

natureconservancy

-1.43

actory

-1.42

techn

-1.40

Reviewer

-1.37

monary

-1.36

leck

-1.36

wcs

-1.35

 courtesy

-1.34

POSITIVE LOGITS

channelAvailability

1.57

 Judgment

1.51

者

1.48

utherford

1.38

eele

1.38

ドラ

1.37

otle

1.31

シャ

1.30

arez

1.29

itans

1.28

Activations Density 0.000%

names of notable individuals, particularly those with the first name "Samuel."

No Comments

No Known Activations