INDEX

Explanations

references to the Drug Enforcement Administration (DEA) and related regulatory issues

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

0:0.17

1:0.04

2:0.06

3:0.05

4:0.06

5:0.05

6:0.19

7:0.12

8:0.02

9:0.08

10:0.05

11:0.06

Negative Logits

orius

-2.88

 Clippers

-2.79

akis

-2.71

 Raptors

-2.62

ustom

-2.58

bridge

-2.48

 tutor

-2.47

 Celtics

-2.46

 prox

-2.46

 etiquette

-2.42

POSITIVE LOGITS

DEA

7.62

 Agents

4.33

 agency

4.23

 agents

4.20

 Agent

3.89

FBI

3.85

 Drug

3.77

 agencies

3.60

Drug

3.59

FBI

3.57

Activations Density 0.004%

references to the Drug Enforcement Administration (DEA) and related regulatory issues

No Comments

No Known Activations