INDEX

Explanations

instances of numeric values or quantities

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

0:0.09

1:0.08

2:0.09

3:0.08

4:0.06

5:0.07

6:0.08

7:0.11

8:0.06

9:0.08

10:0.08

11:0.07

Negative Logits

Syd

-2.96

 Mara

-2.86

 Eden

-2.81

 Fran

-2.68

 Waters

-2.64

Dra

-2.60

 Emer

-2.58

Har

-2.57

Nev

-2.56

 Bene

-2.51

POSITIVE LOGITS

TPP

4.27

PLA

3.26

BTC

3.24

IU

2.88

CF

2.87

PF

2.84

RFC

2.72

Cub

2.71

iOS

2.71

�

2.71

Activations Density 0.000%

instances of numeric values or quantities

No Comments

No Known Activations