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

1:0.11

2:0.07

3:0.07

4:0.07

5:0.07

6:0.07

7:0.09

8:0.09

9:0.08

10:0.08

11:0.07

Negative Logits

quickShipAvailable

-2.10

 Bern

-1.83

 leve

-1.77

 gulf

-1.76

 Providence

-1.70

 springs

-1.70

 whistleblower

-1.64

Attorney

-1.63

 valves

-1.61

 deaf

-1.60

POSITIVE LOGITS

romeda

2.20

plet

2.03

mble

2.00

atro

1.97

 exha

1.95

aditional

1.88

emetery

1.85

alogue

1.84

illet

1.84

arettes

1.84

Activations Density 0.000%

No Known Activations

This feature has no known activations.