INDEX

Explanations

words indicating agreement or adequacy

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_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.07

1:0.09

2:0.07

3:0.08

4:0.07

5:0.08

6:0.05

7:0.09

8:0.07

9:0.08

10:0.09

11:0.09

Negative Logits

cffff

-2.56

METHOD

-2.41

ONSORED

-2.39

checked

-2.35

tec

-2.34

cise

-2.29

yip

-2.28

vag

-2.27

-2.24

plet

-2.18

POSITIVE LOGITS

 Trilogy

2.19

fri

2.17

 Sons

2.14

@@

2.08

 Mour

2.07

 flagship

2.07

 Juno

2.05

 helm

2.05

Grey

2.04

 gallery

2.03

Activations Density 0.000%

words indicating agreement or adequacy

No Comments

No Known Activations