INDEX

Explanations

phrases related to decision-making and options

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

0:0.24

1:0.07

2:0.08

3:0.04

4:0.06

5:0.02

6:0.05

7:0.12

8:0.03

9:0.04

10:0.09

11:0.10

Negative Logits

 Rubio

-3.30

 Silva

-3.21

 Petro

-3.12

│

-3.07

stall

-3.05

 Grac

-3.04

�

-3.00

 Daytona

-3.00

 Rubin

-2.98

Fab

-2.97

POSITIVE LOGITS

 arrows

7.96

 arrow

7.45

 Arrows

6.29

 bows

5.51

 Arrow

5.16

bow

5.10

 Archer

4.95

 Bows

4.61

bows

4.52

bow

4.45

Activations Density 0.002%

phrases related to decision-making and options

No Comments

No Known Activations