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

2:0.08

3:0.08

4:0.08

5:0.09

6:0.09

7:0.08

8:0.07

9:0.09

10:0.07

11:0.07

Negative Logits

ertodd

-1.75

ASHINGTON

-1.58

staking

-1.57

ationally

-1.56

stanbul

-1.53

inburgh

-1.49

hester

-1.47

ariat

-1.42

angelo

-1.41

imentary

-1.40

POSITIVE LOGITS

mia

1.54

 guiName

1.53

eries

1.46

prison

1.41

imm

1.34

mor

1.31

Ev

1.30

reci

1.29

ゼウス

1.28

Rob

1.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.