INDEX

Explanations

phrases and structures that indicate thoughts or reflections in a narrative or statement

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

1:0.02

2:0.09

3:0.07

4:0.09

5:0.03

6:0.04

7:0.39

8:0.04

9:0.03

10:0.07

11:0.07

Negative Logits

WF

-1.50

ickr

-1.46

 backbone

-1.32

Beta

-1.32

TPS

-1.30

Street

-1.28

esters

-1.28

arta

-1.27

 Evidence

-1.24

 Prot

-1.24

POSITIVE LOGITS

覚醒

1.62

 possibilities

1.55

 hypot

1.55

ceivable

1.54

 imminent

1.49

 impending

1.49

 possibility

1.41

 probabilities

1.40

 clutter

1.38

minent

1.38

Activations Density 0.002%

phrases and structures that indicate thoughts or reflections in a narrative or statement

No Comments

No Known Activations