INDEX

Explanations

references to specific individuals and names

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

0:0.03

1:0.03

2:0.08

3:0.22

4:0.02

5:0.03

6:0.14

7:0.15

8:0.04

9:0.07

10:0.07

11:0.08

Negative Logits

staking

-1.17

pedia

-1.12

 incub

-1.09

mercial

-1.07

 Bihar

-1.07

tumblr

-1.05

anamo

-1.03

 sidx

-1.00

aciously

-0.99

idious

-0.98

POSITIVE LOGITS

baum

1.30

 Associates

1.10

pri

1.08

ゴン

1.07

lander

1.05

Seg

1.05

ITNESS

1.04

zyk

1.00

Fram

0.97

ke

0.96

Activations Density 0.005%

references to specific individuals and names

No Comments

No Known Activations