INDEX

Explanations

names and references related to specific individuals and 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_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

1:0.06

2:0.05

3:0.05

4:0.04

5:0.03

6:0.05

7:0.37

8:0.03

9:0.05

10:0.06

11:0.05

Negative Logits

alg

-4.24

gall

-3.88

Gall

-3.82

 gall

-3.78

 Gallagher

-3.69

GC

-3.37

 Gall

-3.36

gal

-3.14

gard

-2.96

lio

-2.83

POSITIVE LOGITS

!--

3.03

 WATCHED

2.91

 <!--

2.88

 Etsy

2.69

 Nich

2.62

etsy

2.59

 Tacoma

2.56

 Mesh

2.55

Wah

2.54

daq

2.46

Activations Density 0.003%

names and references related to specific individuals and events

No Comments

No Known Activations