INDEX

Explanations

instances of the letter 's'

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

6:0.06

7:0.08

8:0.09

9:0.08

10:0.07

11:0.09

Negative Logits

DragonMagazine

-2.84

nesota

-2.75

igers

-2.60

ANC

-2.55

 Kali

-2.52

 Morales

-2.47

 Palin

-2.47

alez

-2.43

 Inquis

-2.33

 blasphemy

-2.28

POSITIVE LOGITS

frame

3.06

��

2.72

glass

2.59

�

2.45

respect

2.40

 WATCH

2.38

coat

2.38

stained

2.38

 Pound

2.33

 Tackle

2.31

Activations Density 0.000%

instances of the letter 's'

No Comments

No Known Activations