INDEX

Explanations

terms related to drag and manipulation in various contexts

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

2:0.09

3:0.27

4:0.02

5:0.02

6:0.08

7:0.12

8:0.07

9:0.09

10:0.05

11:0.10

Negative Logits

 kosher

-1.20

oulos

-1.19

 Ramadan

-1.18

 charitable

-1.12

 deductible

-1.11

 philanthrop

-1.11

��

-1.10

 condol

-1.09

 trusts

-1.09

 newsletters

-1.07

POSITIVE LOGITS

udo

1.26

️

1.21

opal

1.18

 Curve

1.17

aders

1.14

 curve

1.13

ィ

1.09

ーテ

1.09

 Reduction

1.08

 Removal

1.05

Activations Density 0.005%

terms related to drag and manipulation in various contexts

No Comments

No Known Activations