INDEX

Explanations

expressions of necessity or obligation

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

2:0.12

3:0.10

4:0.12

5:0.03

6:0.09

7:0.27

8:0.03

9:0.03

10:0.05

11:0.08

Negative Logits

redited

-1.62

 Causes

-1.46

 Loss

-1.43

 Died

-1.34

ufact

-1.29

 Winning

-1.29

odiac

-1.27

 Worst

-1.25

 Journals

-1.25

 Debt

-1.24

POSITIVE LOGITS

 excuses

1.55

 imports

1.50

 anymore

1.48

 hesitation

1.48

 interrupt

1.48

ptions

1.47

 shielding

1.46

 invitations

1.46

 intrusion

1.45

 safeguards

1.45

Activations Density 0.003%

expressions of necessity or obligation

No Comments

No Known Activations