INDEX

Explanations

technical formats and specifications related to programming or data structuring

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

Head Attr Weights

0:0.13

1:0.09

2:0.07

3:0.06

4:0.06

5:0.04

6:0.11

7:0.13

8:0.04

9:0.04

10:0.05

11:0.13

Negative Logits

 sympath

-2.75

cule

-2.50

 Vale

-2.49

 Cher

-2.44

 Sophia

-2.41

 Chad

-2.39

Blake

-2.36

 malaria

-2.35

ompl

-2.34

 Michele

-2.33

POSITIVE LOGITS

 format

5.80

 Format

5.64

Format

5.16

 formats

5.13

 formatted

4.77

format

4.76

 formatting

4.54

 Template

3.53

Template

3.06

fmt

3.04

Activations Density 0.004%

technical formats and specifications related to programming or data structuring

No Known Activations