INDEX

Explanations

keywords related to medical and health issues, specifically concerning the impact and recognition of certain conditions

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

0:0.02

1:0.03

2:0.35

3:0.07

4:0.14

5:0.05

6:0.02

7:0.10

8:0.08

9:0.04

10:0.03

11:0.02

Negative Logits

hya

-2.68

*/

-2.49

scl

-2.49

iott

-2.46

usercontent

-2.44

soDeliveryDate

-2.37

otos

-2.36

":"/

-2.35

ディ

-2.33

yssey

-2.29

POSITIVE LOGITS

10.11

8.28

[/

8.14

["

7.97

[/

7.65

[-

7.05

['

6.99

 [...]

6.86

[*

6.74

)[

6.60

Activations Density 0.261%

keywords related to medical and health issues, specifically concerning the impact and recognition of certain conditions

No Comments

No Known Activations