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

0:0.07

1:0.07

2:0.07

3:0.08

4:0.08

5:0.07

6:0.10

7:0.09

8:0.08

9:0.09

10:0.08

11:0.07

Negative Logits

 vampire

-3.55

 Horus

-3.44

 Torch

-3.34

 sorcerer

-3.10

 Loki

-3.09

 barb

-2.87

 scorp

-2.84

 looted

-2.74

 Dracula

-2.73

 torch

-2.72

POSITIVE LOGITS

 Parent

3.10

Coach

2.85

Topics

2.84

Newsletter

2.80

Cour

2.80

ews

2.77

osate

2.75

annie

2.75

 Emails

2.73

annel

2.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.