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

0:0.08

1:0.09

2:0.08

3:0.09

4:0.09

5:0.07

6:0.08

7:0.09

8:0.06

9:0.07

10:0.09

11:0.07

Negative Logits

enhagen

-2.02

anyahu

-1.95

afort

-1.94

itbart

-1.88

 Sponsor

-1.68

anamo

-1.62

mares

-1.62

istar

-1.59

atel

-1.55

isodes

-1.51

POSITIVE LOGITS

 rhythm

1.75

 reckoning

1.63

 respons

1.57

 turnover

1.56

 fencing

1.55

ⓘ

1.53

 reperto

1.51

 waking

1.49

 consciousness

1.48

 visitation

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.