INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.09

2:0.08

3:0.07

4:0.10

5:0.08

6:0.08

7:0.07

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

Episode

-1.52

(?,

-1.37

 starring

-1.33

 Comedy

-1.33

 synth

-1.31

 chords

-1.30

ウス

-1.29

FX

-1.24

 Majesty

-1.24

 whopping

-1.23

POSITIVE LOGITS

azo

1.48

��

1.47

 subcontract

1.46

]"

1.41

 elector

1.33

ESE

1.31

)]

1.31

EStreamFrame

1.31

="/

1.28

=]

1.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.