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

0:0.08

1:0.08

2:0.07

3:0.08

4:0.07

5:0.09

6:0.08

7:0.08

8:0.07

9:0.09

10:0.08

11:0.09

Negative Logits

////////

-3.04

 vend

-2.69

 violates

-2.67

owe

-2.65

psons

-2.54

////////////////

-2.52

iques

-2.51

paw

-2.46

sab

-2.45

 sweats

-2.44

POSITIVE LOGITS

 Howell

2.77

 Maid

2.74

 Atkinson

2.74

��

2.71

adiq

2.63

 Giul

2.58

 Hatt

2.56

 Thames

2.55

 Shepherd

2.55

 Marian

2.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.