INDEX

Explanations

punctuation marks at the end of sentences

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

0:0.02

1:0.01

2:0.28

3:0.05

4:0.04

5:0.02

6:0.23

7:0.08

8:0.06

9:0.04

10:0.07

11:0.06

Negative Logits

Seg

-1.52

 punishable

-1.49

imester

-1.48

CLASSIFIED

-1.44

TBA

-1.44

XD

-1.39

 Schedule

-1.37

agraph

-1.34

UTC

-1.34

 Kislyak

-1.32

POSITIVE LOGITS

famous

1.82

schild

1.73

ipeg

1.64

sein

1.59

library

1.54

elight

1.53

ibi

1.52

wic

1.52

orns

1.51

kamp

1.49

Activations Density 0.001%

punctuation marks at the end of sentences

No Comments

No Known Activations