INDEX

Explanations

terms related to addiction treatment and healthcare access

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

0:0.19

1:0.10

2:0.07

3:0.06

4:0.10

5:0.03

6:0.07

7:0.13

8:0.02

9:0.05

10:0.07

11:0.07

Negative Logits

�

-3.01

inventoryQuantity

-2.88

notations

-2.77

 GOODMAN

-2.69

�

-2.69

 Thib

-2.63

 Ellison

-2.63

scl

-2.60

antry

-2.60

orsi

-2.58

POSITIVE LOGITS

 addiction

6.53

 addicts

6.34

 Addiction

6.20

 addicted

6.16

 addict

5.96

 addictive

5.39

 relapse

4.46

 detox

4.41

 abstinence

4.33

 Substance

4.18

Activations Density 0.025%

terms related to addiction treatment and healthcare access

No Comments

No Known Activations