INDEX

Explanations

phrases related to the context and details of events or actions

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.22

1:0.06

2:0.08

3:0.06

4:0.03

5:0.03

6:0.07

7:0.16

8:0.03

9:0.04

10:0.11

11:0.06

Negative Logits

 fructose

-2.98

fruit

-2.68

 Lisp

-2.63

龍�

-2.58

 caffe

-2.55

 Clojure

-2.54

�

-2.53

 diaper

-2.49

cup

-2.47

Android

-2.47

POSITIVE LOGITS

MGM

7.71

 Mandal

4.18

Las

3.78

 casinos

3.62

 casino

3.56

Wyn

3.49

 Vegas

3.47

Las

3.46

 Coyotes

3.44

 Casino

3.42

Activations Density 0.001%

phrases related to the context and details of events or actions

No Comments

No Known Activations