INDEX

Explanations

references to reasonable actions or decisions made by individuals

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

2:0.09

3:0.06

4:0.08

5:0.02

6:0.25

7:0.21

8:0.03

9:0.03

10:0.11

11:0.05

Negative Logits

ModLoader

-1.48

��

-1.47

kok

-1.44

forth

-1.37

 Fever

-1.35

天

-1.32

wikipedia

-1.32

 goodbye

-1.29

along

-1.29

ヘ

-1.29

POSITIVE LOGITS

VPN

1.48

 unbiased

1.45

 apprehend

1.43

reasonable

1.42

 assumptions

1.38

ifiable

1.38

ensical

1.36

 dissu

1.34

uitive

1.33

 Modest

1.32

Activations Density 0.008%

references to reasonable actions or decisions made by individuals

No Comments

No Known Activations