INDEX

Explanations

the article "a"

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

3:0.07

4:0.10

5:0.08

6:0.09

7:0.07

8:0.08

9:0.09

10:0.09

11:0.07

Negative Logits

Bug

-2.96

BOX

-2.90

 Rated

-2.85

 Trem

-2.79

 Plug

-2.77

 Package

-2.75

Box

-2.73

 Rhod

-2.71

 Rule

-2.71

UPS

-2.68

POSITIVE LOGITS

cean

2.83

elong

2.78

CHQ

2.70

ヘ

2.69

anyahu

2.62

Lie

2.58

��

2.56

casts

2.51

dinand

2.51

LEASE

2.49

Activations Density 0.000%

the article "a"

No Comments

No Known Activations