INDEX

Explanations

words related to specific locations or buildings

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.07

1:0.07

2:0.09

3:0.07

4:0.08

5:0.10

6:0.08

7:0.07

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

reb

-2.76

?".

-2.65

 Baton

-2.64

 Archdemon

-2.58

sis

-2.58

 Bind

-2.56

sb

-2.55

igible

-2.50

 Certified

-2.44

 Brennan

-2.42

POSITIVE LOGITS

Tweet

2.45

tom

2.37

HOME

2.21

Shu

2.20

India

2.19

 brilliance

2.16

 envy

2.15

 metaphors

2.15

Luck

2.15

��

2.14

Activations Density 0.000%

words related to specific locations or buildings

No Comments

No Known Activations