INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.08

2:0.08

3:0.07

4:0.07

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.09

11:0.09

Negative Logits

NRS

-2.84

SHE

-2.74

ella

-2.73

ACTED

-2.57

 POLITICO

-2.51

GREEN

-2.49

esses

-2.45

atis

-2.42

 Moroc

-2.37

 Neal

-2.34

POSITIVE LOGITS

 Tent

2.64

Torrent

2.52

roid

2.50

 Leaf

2.44

 crem

2.41

 Nest

2.40

 tents

2.31

 Lash

2.27

electric

2.25

cloth

2.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.