INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

1:0.07

2:0.07

3:0.10

4:0.09

5:0.07

6:0.09

7:0.11

8:0.07

9:0.07

10:0.06

11:0.06

Negative Logits

 guiActiveUnfocused

-2.87

Poké

-2.68

›

-2.62

 Appears

-2.49

ometer

-2.36

 Tanner

-2.35

escription

-2.33

 migr

-2.29

estamp

-2.28

 explor

-2.27

POSITIVE LOGITS

SEC

2.90

 Addiction

2.89

 Ares

2.75

AIDS

2.62

 Ukrain

2.61

 Fury

2.56

 subordinates

2.55

 Integrity

2.51

FS

2.50

 Dodd

2.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.