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

3:0.09

4:0.07

5:0.09

6:0.08

7:0.07

8:0.09

9:0.08

10:0.09

11:0.06

Negative Logits

aires

-1.85

untled

-1.72

akings

-1.67

odes

-1.67

oud

-1.64

imity

-1.63

bably

-1.61

uer

-1.61

anches

-1.60

ezvous

-1.57

POSITIVE LOGITS

 gears

1.74

ModLoader

1.69

 emulation

1.57

isSpecialOrderable

1.54

 repe

1.45

maxwell

1.43

 Rodrig

1.39

 Sanskrit

1.36

fixes

1.36

 defe

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.