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

1:0.08

2:0.08

3:0.06

4:0.09

5:0.07

6:0.08

7:0.07

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

 Cosponsors

-2.29

sts

-1.92

 Shows

-1.79

 Parts

-1.76

 Correspond

-1.74

 Admir

-1.72

RM

-1.69

atures

-1.69

 palp

-1.68

rs

-1.68

POSITIVE LOGITS

lier

1.88

BUS

1.66

 diffusion

1.63

 multiplication

1.61

 fewer

1.60

icable

1.57

 lasting

1.56

growth

1.56

 costing

1.54

 horm

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.