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

2:0.07

3:0.09

4:0.08

5:0.08

6:0.09

7:0.07

8:0.07

9:0.09

10:0.07

11:0.09

Negative Logits

 Bates

-3.69

 Scrolls

-2.74

 treadmill

-2.72

::::::::

-2.68

 Clicker

-2.67

Bed

-2.66

 clocks

-2.63

 Sims

-2.62

 Clockwork

-2.61

vac

-2.54

POSITIVE LOGITS

iferation

3.01

Newsletter

2.63

 Bride

2.53

án

2.49

ru

2.49

Bernie

2.46

ospels

2.46

orsche

2.45

weapons

2.44

ennial

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.