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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.09

5:0.08

6:0.09

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

independence

-1.68

 cryst

-1.64

independent

-1.62

ependence

-1.60

 Madness

-1.59

equality

-1.58

 Cinderella

-1.55

★★

-1.55

 Rosen

-1.54

entity

-1.52

POSITIVE LOGITS

oğ

1.82

externalActionCode

1.80

racuse

1.70

pel

1.59

 interchange

1.58

RNA

1.56

 aboard

1.55

ospons

1.53

Amb

1.52

ounter

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.