INDEX

Explanations

references to blindness or ignoring significant information

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.05

1:0.02

2:0.22

3:0.05

4:0.34

5:0.03

6:0.02

7:0.02

8:0.05

9:0.09

10:0.04

11:0.02

Negative Logits

��

-1.94

pei

-1.78

alli

-1.72

�

-1.66

auri

-1.58

�

-1.55

nai

-1.48

ás

-1.48

án

-1.47

ua

-1.47

POSITIVE LOGITS

 irony

1.51

 parody

1.50

 imitation

1.39

 mystery

1.38

 Musk

1.38

 illusion

1.35

 blaster

1.33

otomy

1.32

 hypocrisy

1.30

 humour

1.30

Activations Density 0.004%

references to blindness or ignoring significant information

No Comments

No Known Activations