INDEX

Explanations

discussions regarding crises and their socioeconomic impacts

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.08

1:0.03

2:0.16

3:0.19

4:0.04

5:0.14

6:0.02

7:0.08

8:0.05

9:0.02

10:0.11

11:0.01

Negative Logits

 testers

-2.00

 Yard

-1.99

 Yards

-1.76

themed

-1.75

 workout

-1.68

Sweet

-1.68

 tattoos

-1.68

 reusable

-1.67

Boo

-1.65

Ded

-1.63

POSITIVE LOGITS

 destabil

3.11

 crisis

3.09

 crises

3.06

 geopolitical

2.82

 catastrophe

2.75

 Crisis

2.63

 irreversible

2.63

 existential

2.58

 worsening

2.58

 catastrophic

2.58

Activations Density 0.981%

discussions regarding crises and their socioeconomic impacts

No Comments

No Known Activations