INDEX

Explanations

references to "behind the scenes" or related phrases

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.02

2:0.08

3:0.28

4:0.01

5:0.02

6:0.11

7:0.05

8:0.08

9:0.10

10:0.06

11:0.13

Negative Logits

ogn

-1.29

KA

-1.21

overe

-1.17

anmar

-1.13

cit

-1.11

iasco

-1.10

bach

-1.10

ashtra

-1.10

clerosis

-1.08

emort

-1.07

POSITIVE LOGITS

Reloaded

1.26

 Shiny

1.24

 ropes

1.13

 Rampage

1.05

Dispatch

1.04

 Mehran

1.03

``

1.00

Alias

0.99

Cache

0.99

Thumbnail

0.98

Activations Density 0.018%

references to "behind the scenes" or related phrases

No Comments

No Known Activations