INDEX

Explanations

references to duration of time, particularly in the context of experiences or service

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

0:0.08

1:0.08

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

XD

-3.33

 Polk

-3.16

dar

-2.96

 Gibbs

-2.74

 Folk

-2.67

 anth

-2.66

DPR

-2.59

Fas

-2.59

DN

-2.57

lar

-2.56

POSITIVE LOGITS

Mess

2.55

etsy

2.50

shake

2.48

sterdam

2.43

isu

2.43

 regrets

2.37

 Zionism

2.36

uckland

2.30

uc

2.30

lu

2.29

Activations Density 0.000%

references to duration of time, particularly in the context of experiences or service

No Comments

No Known Activations