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

2:0.07

3:0.09

4:0.06

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

hower

-2.00

odox

-1.99

ixties

-1.93

ongevity

-1.90

akespe

-1.85

acci

-1.85

undown

-1.83

illac

-1.82

leness

-1.81

owship

-1.81

POSITIVE LOGITS

 inference

1.70

 Haram

1.55

 caching

1.54

 subcontract

1.53

 polyg

1.52

 reporting

1.52

 coloring

1.51

 uploading

1.50

Gw

1.49

 redd

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.