INDEX

Explanations

references to the act of shooting or firing weapons

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

2:0.05

3:0.05

4:0.25

5:0.03

6:0.09

7:0.11

8:0.04

9:0.04

10:0.15

11:0.09

Negative Logits

iterranean

-1.62

ertain

-1.59

icent

-1.48

banks

-1.36

 tradem

-1.35

 Macedonia

-1.33

accessible

-1.29

ould

-1.28

 Nadu

-1.27

ossier

-1.26

POSITIVE LOGITS

agraph

1.79

 bursts

1.68

 breaths

1.51

 increments

1.48

 grenades

1.45

 sigh

1.45

 darts

1.45

 strokes

1.41

 explos

1.41

 blasts

1.39

Activations Density 0.020%

references to the act of shooting or firing weapons

No Comments

No Known Activations