INDEX

Explanations

references to specific works or titles, particularly related to "Twin Peaks" and other films or series by David Lynch

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.13

1:0.02

2:0.15

3:0.07

4:0.04

5:0.07

6:0.07

7:0.05

8:0.19

9:0.06

10:0.04

11:0.05

Negative Logits

Ukraine

-3.85

orgetown

-3.57

export

-3.22

【

-3.18

 Crimea

-3.16

Iv

-3.09

Gaza

-3.06

Ky

-3.04

ovych

-3.04

estyle

-3.02

POSITIVE LOGITS

 Twin

5.40

 Scully

4.96

 Peaks

4.87

 Bigfoot

4.24

 Lynch

4.18

FD

4.17

 Laura

4.15

UFO

3.76

 Oswald

3.75

 Lodge

3.63

Activations Density 0.002%

references to specific works or titles, particularly related to "Twin Peaks" and other films or series by David Lynch

No Comments

No Known Activations