INDEX

Explanations

references to significant numerical values or statistics

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

2:0.17

3:0.09

4:0.01

5:0.02

6:0.12

7:0.24

8:0.06

9:0.04

10:0.03

11:0.14

Negative Logits

Islamic

-1.24

igmat

-1.21

emort

-1.18

League

-1.10

 exact

-1.08

christ

-1.05

advertising

-1.02

exempt

-1.01

 isEnabled

-1.01

 ministry

-0.99

POSITIVE LOGITS

otos

1.44

TOD

1.21

ymes

1.15

ooting

1.13

 centrif

1.12

 unfocusedRange

1.12

izont

1.07

umbered

1.05

HDL

1.04

UES

1.04

Activations Density 0.113%

references to significant numerical values or statistics

No Comments

No Known Activations