INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.07

2:0.08

3:0.08

4:0.09

5:0.07

6:0.07

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

alion

-2.17

Panel

-1.90

usk

-1.89

EMBER

-1.84

pair

-1.82

posium

-1.80

folio

-1.73

opal

-1.72

urry

-1.72

ppel

-1.70

POSITIVE LOGITS

hog

2.16

1.79

 brisk

1.71

 Adren

1.70

 rhet

1.68

 charact

1.68

 PROG

1.65

 pharm

1.61

 hypoc

1.60

 mant

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.