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

0:0.07

1:0.08

2:0.07

3:0.07

4:0.08

5:0.08

6:0.08

7:0.10

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

 cancell

-1.85

 retaining

-1.74

 contrace

-1.67

 compr

-1.65

 divid

-1.65

�醒

-1.61

 lett

-1.59

 bulk

-1.57

 bund

-1.55

 cance

-1.52

POSITIVE LOGITS

SPONSORED

2.37

soever

2.00

Posts

1.92

Redd

1.88

bernatorial

1.85

����

1.84

cause

1.82

ipedia

1.81

mods

1.81

thood

1.80

Activations Density 0.000%

No Known Activations

This feature has no known activations.