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

0:0.07

1:0.08

2:0.07

3:0.10

4:0.07

5:0.09

6:0.10

7:0.07

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

awa

-2.88

ta

-2.80

pton

-2.72

WARE

-2.61

]+

-2.60

jad

-2.54

orgetown

-2.53

-2.46

rame

-2.45

 coun

-2.40

POSITIVE LOGITS

geon

3.16

黒

2.88

闘

2.80

umerable

2.80

wolves

2.71

 Yugoslavia

2.67

osaurs

2.61

 Rodgers

2.52

angel

2.51

lier

2.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.