INDEX

Explanations

names of individuals associated with quotes or statements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.03

2:0.09

3:0.14

4:0.25

5:0.07

6:0.04

7:0.02

8:0.05

9:0.10

10:0.07

11:0.05

Negative Logits

 footprint

-1.42

 slate

-1.42

 invading

-1.37

 inappropriately

-1.36

 Olympics

-1.33

MMR

-1.31

 contamin

-1.30

 geographically

-1.28

 offensively

-1.28

 bandwagon

-1.27

POSITIVE LOGITS

pedia

1.66

1.62

reon

1.55

�

1.50

minecraft

1.49

SourceFile

1.42

Wiki

1.41

��

1.41

 exclaimed

1.38

Boss

1.37

Activations Density 0.154%

names of individuals associated with quotes or statements

No Comments

No Known Activations