INDEX

Explanations

references to features and qualities of writing instruments and paper

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.29

1:0.05

2:0.08

3:0.04

4:0.05

5:0.03

6:0.08

7:0.09

8:0.03

9:0.04

10:0.09

11:0.08

Negative Logits

 Chern

-3.89

 Sagan

-3.77

 Kasich

-3.60

 Curry

-3.58

Gow

-3.42

 Cosmos

-3.36

 McMahon

-3.36

Rao

-3.29

 Chandra

-3.26

obyl

-3.25

POSITIVE LOGITS

 pens

7.94

pen

7.62

ink

6.86

 Pens

6.17

Ink

6.01

Pen

5.87

 fountain

5.75

Pen

5.70

 pencil

5.67

nib

5.59

Activations Density 0.013%

references to features and qualities of writing instruments and paper

No Comments

No Known Activations