INDEX

Explanations

the word "of"

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

0:0.09

1:0.09

2:0.08

3:0.07

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

PID

-2.88

thro

-2.79

nces

-2.62

geons

-2.57

boss

-2.52

Target

-2.38

Opt

-2.35

fml

-2.32

rift

-2.31

Boss

-2.31

POSITIVE LOGITS

 Levy

2.68

ograph

2.67

 Stain

2.67

iferation

2.35

aganda

2.35

 correlation

2.35

 patriotic

2.29

 unification

2.29

2.27

 patriotism

2.27

Activations Density 0.000%

the word "of"

No Comments

No Known Activations