INDEX

Explanations

references to circuses and associated imagery or elements

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

0:0.20

1:0.06

2:0.05

3:0.06

4:0.06

5:0.03

6:0.12

7:0.10

8:0.04

9:0.05

10:0.09

11:0.08

Negative Logits

 Cortana

-3.02

 Vapor

-2.93

 targ

-2.92

SAM

-2.92

UM

-2.83

HUD

-2.82

UD

-2.81

�

-2.79

 Halo

-2.78

 Zheng

-2.77

POSITIVE LOGITS

 Circus

7.27

 circus

7.11

 clown

4.49

 elephants

4.24

 circ

4.01

 Clown

3.86

 juggling

3.62

 elephant

3.54

 Muss

3.46

 performers

3.43

Activations Density 0.004%

references to circuses and associated imagery or elements

No Comments

No Known Activations