INDEX

Explanations

mentions of social media interactions and references

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

1:0.02

2:0.07

3:0.03

4:0.05

5:0.03

6:0.21

7:0.06

8:0.10

9:0.22

10:0.02

11:0.04

Negative Logits

ajor

-4.07

eele

-3.64

imbabwe

-3.54

bar

-3.40

Kov

-3.32

enta

-3.31

azel

-3.19

urai

-3.19

 Berman

-3.13

mington

-3.13

POSITIVE LOGITS

 Sophia

9.25

 Sophie

7.39

Sof

4.65

 soph

4.43

 Soph

4.42

oph

4.10

CPS

4.05

 Emma

3.94

Rap

3.90

 Panc

3.85

Activations Density 0.001%

mentions of social media interactions and references

No Comments

No Known Activations