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

1:0.10

2:0.07

3:0.08

4:0.08

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.06

11:0.08

Negative Logits

issan

-2.58

ever

-2.52

ropolitan

-2.47

orp

-2.45

grand

-2.44

sych

-2.38

 bankrupt

-2.37

rolet

-2.35

ech

-2.35

weak

-2.33

POSITIVE LOGITS

 danced

2.89

rette

2.79

 dyed

2.68

Db

2.67

umbnails

2.66

 Crowley

2.62

jee

2.61

Phi

2.59

pee

2.48

soDeliveryDate

2.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.