INDEX

Explanations

instances of the word "in," indicating it is looking for locational or contextual phrases

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

0:0.02

1:0.02

2:0.09

3:0.05

4:0.09

5:0.02

6:0.06

7:0.33

8:0.03

9:0.05

10:0.09

11:0.09

Negative Logits

Kro

-1.72

 pharmacies

-1.49

 Leban

-1.48

awatts

-1.47

eez

-1.45

itta

-1.44

glers

-1.42

undown

-1.42

pload

-1.42

yden

-1.42

POSITIVE LOGITS

 Attribution

1.78

 preserving

1.58

 righteousness

1.55

 disclaim

1.51

 disav

1.42

 educating

1.41

 fidelity

1.40

 Computing

1.40

 preservation

1.39

 existential

1.37

Activations Density 0.001%

instances of the word "in," indicating it is looking for locational or contextual phrases

No Comments

No Known Activations