INDEX

Explanations

references to counts or quantities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.07

9:0.08

10:0.09

11:0.09

Negative Logits

 advance

-2.28

 condem

-2.28

ascript

-2.21

 premiere

-2.15

 markup

-2.13

 conven

-2.13

 tremend

-2.13

 authenticated

-2.11

 authorize

-2.10

 prompts

-2.08

POSITIVE LOGITS

hower

2.46

 Waterloo

2.36

�

2.29

 Weber

2.17

龍

2.17

 Tiger

2.12

 Valhalla

2.11

 Horizon

2.07

Vij

2.06

��

2.03

Activations Density 0.000%

references to counts or quantities

No Comments

No Known Activations