INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

1:0.07

2:0.08

3:0.07

4:0.07

5:0.08

6:0.09

7:0.10

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

Dash

-1.71

cgi

-1.44

APD

-1.40

 nudity

-1.38

Url

-1.37

ell

-1.34

bay

-1.33

iler

-1.33

mp

-1.31

title

-1.31

POSITIVE LOGITS

 Jinping

1.61

 salv

1.59

 Canaver

1.58

akening

1.53

 fract

1.52

ologically

1.48

 Leilan

1.47

IRED

1.44

edient

1.43

intention

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.