INDEX

Explanations

phrases indicating blame or responsibility

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_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

1:0.01

2:0.15

3:0.05

4:0.21

5:0.02

6:0.04

7:0.19

8:0.04

9:0.03

10:0.04

11:0.14

Negative Logits

inventoryQuantity

-1.38

 seriousness

-1.34

 actionGroup

-1.34

 decency

-1.29

odan

-1.29

urances

-1.24

 simultane

-1.19

cookie

-1.19

 disclaimer

-1.17

VOL

-1.16

POSITIVE LOGITS

LH

1.28

ndum

1.23

minist

1.15

inic

1.14

owered

1.14

IST

1.14

SOM

1.13

 Greenwich

1.12

 Shining

1.12

lift

1.12

Activations Density 0.001%

phrases indicating blame or responsibility

No Comments

No Known Activations