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

1:0.06

2:0.09

3:0.07

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

selage

-1.82

gram

-1.80

ika

-1.76

vd

-1.75

rd

-1.73

iaz

-1.71

bd

-1.71

nex

-1.71

oute

-1.68

sole

-1.68

POSITIVE LOGITS

 hiber

1.72

 accomplishment

1.49

�

1.49

 prov

1.49

 suprem

1.48

ERAL

1.46

 classics

1.44

 improbable

1.43

fut

1.43

RW

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.