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

1:0.06

2:0.07

3:0.08

4:0.08

5:0.10

6:0.09

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

Maker

-2.10

gam

-2.00

戦

-1.89

fighters

-1.63

COR

-1.63

stuff

-1.61

cor

-1.59

independence

-1.59

Understanding

-1.57

 LEDs

-1.56

POSITIVE LOGITS

igham

1.97

ecast

1.92

zech

1.86

 Cosponsors

1.84

bnb

1.78

 sidx

1.76

 visa

1.72

ifax

1.71

ultural

1.70

 Lumpur

1.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.