INDEX

Explanations

phrases related to quantity or volume

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

1:0.06

2:0.08

3:0.08

4:0.06

5:0.08

6:0.08

7:0.08

8:0.09

9:0.09

10:0.09

11:0.07

Negative Logits

zai

-3.52

abama

-2.99

rack

-2.83

Dak

-2.82

jong

-2.78

ilitary

-2.69

anyahu

-2.61

 retali

-2.58

ğ

-2.54

 Hacker

-2.52

POSITIVE LOGITS

love

2.68

acea

2.59

 Naples

2.56

 affection

2.52

 Visit

2.50

 phil

2.48

ppings

2.41

Love

2.40

 Philipp

2.39

 transplant

2.36

Activations Density 0.000%

phrases related to quantity or volume

No Comments

No Known Activations