INDEX

Explanations

references to social or political pressure

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

0:0.43

1:0.01

2:0.19

3:0.06

4:0.02

5:0.05

6:0.02

7:0.03

8:0.02

9:0.02

10:0.08

11:0.02

Negative Logits

 annot

-2.90

 annotations

-2.77

 drawings

-2.35

GIF

-2.29

 fram

-2.29

 mosa

-2.27

 curator

-2.27

 sketch

-2.24

 plot

-2.24

 Satoshi

-2.20

POSITIVE LOGITS

 exerted

2.77

Factor

2.69

pressure

2.57

 pressuring

2.55

 pressure

2.38

itri

2.36

campaign

2.30

helle

2.27

 intensify

2.24

 Pressure

2.24

Activations Density 0.043%

references to social or political pressure

No Comments

No Known Activations