INDEX

Explanations

references to action and engagement in activities

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

0:0.05

1:0.03

2:0.10

3:0.07

4:0.03

5:0.04

6:0.03

7:0.03

8:0.46

9:0.03

10:0.03

11:0.03

Negative Logits

 Zion

-4.22

 Zionist

-4.17

 Zionism

-4.09

 Netanyahu

-3.97

 Israelis

-3.71

 cricket

-3.69

IDF

-3.61

 Israeli

-3.50

 Jewish

-3.50

 Israel

-3.42

POSITIVE LOGITS

UFC

4.06

UFC

3.77

 Silva

3.51

MMA

3.41

Sao

3.20

 Wander

3.17

 Cyborg

3.06

otine

2.96

 Dill

2.96

nen

2.96

Activations Density 0.072%

references to action and engagement in activities

No Comments

No Known Activations