INDEX

Explanations

references to notable individuals and their achievements

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

0:0.21

1:0.08

2:0.06

3:0.04

4:0.04

5:0.02

6:0.09

7:0.13

8:0.03

9:0.05

10:0.13

11:0.05

Negative Logits

 Spiral

-3.10

TC

-2.92

 Dickinson

-2.91

 Shan

-2.85

 Progressive

-2.80

 Rochester

-2.76

��

-2.76

 Dayton

-2.75

 interns

-2.71

 Dartmouth

-2.70

POSITIVE LOGITS

 Bale

9.04

 Gareth

5.80

 Ronaldo

4.49

 Bane

4.01

 Spurs

3.93

 Wales

3.90

 Benz

3.89

 Tottenham

3.88

 Welsh

3.88

 Crist

3.78

Activations Density 0.002%

references to notable individuals and their achievements

No Comments

No Known Activations