INDEX

Explanations

contact information for support and emergency services

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.03

1:0.01

2:0.06

3:0.05

4:0.07

5:0.03

6:0.05

7:0.17

8:0.03

9:0.05

10:0.31

11:0.09

Negative Logits

 Rebellion

-1.74

 hindsight

-1.68

amount

-1.62

 gamb

-1.59

 symmetry

-1.59

 vengeance

-1.59

 hips

-1.55

 athleticism

-1.51

 shader

-1.50

advant

-1.50

POSITIVE LOGITS

staff

2.15

 hotline

2.04

Emergency

1.96

 staffed

1.95

 referral

1.68

CST

1.67

secure

1.67

Alert

1.67

email

1.61

 Emergency

1.59

Activations Density 0.000%

contact information for support and emergency services

No Comments

No Known Activations