INDEX

Explanations

professions or roles related to leadership and organization

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

2:0.03

3:0.04

4:0.04

5:0.08

6:0.03

7:0.03

8:0.02

9:0.54

10:0.02

11:0.09

Negative Logits

ECD

-2.28

 ACTIONS

-2.02

amsung

-1.96

=~=~

-1.95

VALUE

-1.94

 Churches

-1.92

agne

-1.87

doms

-1.87

rarily

-1.85

ONDON

-1.85

POSITIVE LOGITS

 manager

3.64

 coordinator

3.59

 spokesman

3.58

 director

3.58

 founder

3.50

 leader

3.50

 frontman

3.49

 announcer

3.47

 curator

3.46

 chairman

3.41

Activations Density 0.834%

professions or roles related to leadership and organization

No Comments

No Known Activations