INDEX

Explanations

the word "of."

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.09

1:0.09

2:0.07

3:0.09

4:0.08

5:0.08

6:0.09

7:0.07

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

 focus

-2.60

ichael

-2.44

Target

-2.42

 targeted

-2.40

geist

-2.40

 Hobby

-2.40

 Hunger

-2.37

requ

-2.37

McH

-2.34

dule

-2.33

POSITIVE LOGITS

Sph

3.04

KGB

3.04

 USSR

3.03

FIA

2.91

Soviet

2.88

 Sanskrit

2.88

jew

2.85

 Tibetan

2.80

Sov

2.75

 Georgian

2.75

Activations Density 0.000%

the word "of."

No Comments

No Known Activations