INDEX

Explanations

references to specific locations and directions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.04

2:0.09

3:0.10

4:0.02

5:0.07

6:0.06

7:0.17

8:0.07

9:0.15

10:0.06

11:0.09

Negative Logits

catentry

-1.39

 respectively

-1.28

@#&

-1.26

 Cluster

-1.24

��

-1.22

cially

-1.19

tains

-1.19

 variance

-1.16

 vend

-1.16

¶

-1.12

POSITIVE LOGITS

 strangers

1.35

 rooft

1.34

enegger

1.29

rily

1.14

giene

1.13

enaries

1.11

opian

1.10

 graves

1.08

=]

1.07

icons

1.07

Activations Density 0.001%

references to specific locations and directions

No Comments

No Known Activations