INDEX

Explanations

statements about the nature of identities and their experiences

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

1:0.11

2:0.07

3:0.07

4:0.04

5:0.07

6:0.05

7:0.06

8:0.02

9:0.22

10:0.11

11:0.03

Negative Logits

ait

-3.14

plin

-2.73

Cla

-2.72

onge

-2.69

 Cord

-2.59

ellen

-2.54

 Leslie

-2.49

 Burlington

-2.48

SpaceEngineers

-2.44

correct

-2.41

POSITIVE LOGITS

zl

3.60

about

3.09

abouts

3.03

 Haku

2.64

About

2.63

mania

2.60

 Desire

2.50

 Newt

2.46

 Cantor

2.41

Moz

2.39

Activations Density 0.008%

statements about the nature of identities and their experiences

No Comments

No Known Activations