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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.07

2:0.08

3:0.08

4:0.09

5:0.08

6:0.08

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

Ago

-3.33

 Logged

-3.06

 Musical

-2.84

esse

-2.64

Bear

-2.56

 Pike

-2.55

Spe

-2.53

mberg

-2.53

pine

-2.50

-2.48

POSITIVE LOGITS

 surf

2.60

 resur

2.48

Dun

2.43

['

2.42

 trustees

2.40

 grappling

2.36

 zipper

2.33

 fights

2.32

 inevitably

2.32

tyr

2.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.