INDEX

Explanations

No Explanations Found

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

3:0.09

4:0.07

5:0.08

6:0.07

7:0.10

8:0.07

9:0.06

10:0.09

11:0.08

Negative Logits

paced

-2.73

 uncontroll

-2.66

vous

-2.63

isode

-2.58

uggle

-2.56

pmwiki

-2.55

�

-2.52

vill

-2.49

Pool

-2.49

 freshmen

-2.48

POSITIVE LOGITS

 Surgery

3.03

OLOGY

2.88

 Research

2.83

 Appeal

2.81

 Revenue

2.80

 Payments

2.79

 Industry

2.76

 Ministry

2.74

 Manufacturing

2.71

 Rehab

2.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.