INDEX

Explanations

instances of collective gatherings or events

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

0:0.10

1:0.04

2:0.06

3:0.09

4:0.05

5:0.04

6:0.20

7:0.16

8:0.02

9:0.05

10:0.08

11:0.06

Negative Logits

 Scully

-2.79

client

-2.69

★★

-2.57

Reviewed

-2.52

 Client

-2.44

Rating

-2.42

 Accounts

-2.40

Blake

-2.37

 Seller

-2.36

 Christensen

-2.31

POSITIVE LOGITS

 march

5.20

 marches

4.66

 marching

4.61

 marched

4.15

 rall

3.68

 rally

3.32

 organizers

3.23

 parade

3.23

 procession

2.95

 rallies

2.94

Activations Density 0.023%

instances of collective gatherings or events

No Comments

No Known Activations