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

0:0.09

1:0.08

2:0.10

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.08

9:0.06

10:0.07

11:0.08

Negative Logits

 Physics

-2.92

 SOFTWARE

-2.85

 Mathematics

-2.84

 IEEE

-2.73

®

-2.72

 Mathemat

-2.71

 Neural

-2.70

TY

-2.68

 Zionism

-2.65

 Enabled

-2.61

POSITIVE LOGITS

quit

3.07

 juggling

3.05

 raids

3.04

 chefs

2.97

 raiding

2.94

 raid

2.87

 hoard

2.78

ItemImage

2.69

 haul

2.68

ullivan

2.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.