INDEX

Explanations

instances of 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

0:0.08

1:0.08

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

Summary

-3.49

Reward

-2.95

Details

-2.86

Shares

-2.69

Steven

-2.68

Wallet

-2.65

Exception

-2.61

Examples

-2.61

summary

-2.59

ifacts

-2.54

POSITIVE LOGITS

 Ukrain

2.94

NK

2.84

mos

2.83

MJ

2.62

 trance

2.60

 electro

2.57

 USSR

2.52

izoph

2.49

 Shogun

2.46

mson

2.43

Activations Density 0.000%

instances of the word "of"

No Comments

No Known Activations