INDEX

Explanations

names of sports teams, specifically football and basketball teams

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.15

1:0.03

2:0.14

3:0.06

4:0.06

5:0.03

6:0.09

7:0.02

8:0.09

9:0.07

10:0.09

11:0.12

Negative Logits

ibal

-1.60

onal

-1.60

ierrez

-1.58

foreseen

-1.52

adr

-1.51

vasive

-1.50

getic

-1.46

oresc

-1.46

orescence

-1.45

andem

-1.44

POSITIVE LOGITS

etc

1.66

NL

1.64

KC

1.62

Rog

1.55

Orange

1.46

 Surf

1.46

review

1.42

Uk

1.41

 Pirates

1.39

MH

1.39

Activations Density 0.005%

names of sports teams, specifically football and basketball teams

No Comments

No Known Activations