INDEX

Explanations

references to legal or political entities as well as specific dates and statistics

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

0:0.03

1:0.01

2:0.02

3:0.22

4:0.02

5:0.03

6:0.05

7:0.03

8:0.02

9:0.01

10:0.46

11:0.04

Negative Logits

.''.

-2.36

.]

-2.23

.</

-2.18

.�

-2.12

.[

-2.09

.:

-2.08

."

-2.06

.}

-1.97

.*

-1.96

.(

-1.95

POSITIVE LOGITS

),

4.73

),

4.51

!),

4.46

)",

4.44

?),

4.41

'),

4.24

),"

4.16

%),

4.09

)),

3.80

"),

3.70

Activations Density 0.236%

references to legal or political entities as well as specific dates and statistics

No Comments

No Known Activations