INDEX

Explanations

the definite article "the"

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

1:0.07

2:0.09

3:0.09

4:0.08

5:0.08

6:0.09

7:0.07

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

Δ

-2.49

-2.30

ACT

-2.28

<|endoftext|>

-2.27

CP

-2.27

 commons

-2.27

 citation

-2.25

 PLoS

-2.24

DOI

-2.23

POSITIVE LOGITS

senal

3.32

 tremend

3.04

urat

2.70

 Mafia

2.62

ilitary

2.60

avez

2.59

Haunted

2.58

afety

2.58

 camouflage

2.58

weapon

2.54

Activations Density 0.000%

the definite article "the"

No Comments

No Known Activations