INDEX

Explanations

references to time and significant historical events

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

0:0.02

1:0.02

2:0.03

3:0.26

4:0.02

5:0.03

6:0.12

7:0.05

8:0.11

9:0.02

10:0.08

11:0.18

Negative Logits

Downloadha

-1.61

aukee

-1.33

ibrary

-1.26

opa

-1.24

Phones

-1.21

Plug

-1.10

umblr

-1.09

 predictive

-1.08

rypt

-1.08

 Puzz

-1.07

POSITIVE LOGITS

wcsstore

1.36

 Creed

1.22

:(

1.16

redients

1.11

 Hurricanes

1.11

iation

1.10

headers

1.09

ittees

1.09

mentioned

1.09

 generations

1.07

Activations Density 0.005%

references to time and significant historical events

No Comments

No Known Activations