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

1:0.08

2:0.08

3:0.08

4:0.07

5:0.07

6:0.09

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 Event

-3.33

 interpret

-2.77

 sham

-2.70

 shaping

-2.69

 promoter

-2.65

 Cycle

-2.62

 Trin

-2.60

 function

-2.60

imb

-2.60

 EVENT

-2.58

POSITIVE LOGITS

[+

3.32

USD

3.26

Marcus

3.08

Mars

2.99

ysis

2.99

 Pell

2.95

 UCHIJ

2.91

netflix

2.90

Shares

2.88

Jen

2.85

Activations Density 0.000%

the article "a"

No Comments

No Known Activations