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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.06

2:0.09

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

akia

-1.84

 mosqu

-1.75

 sclerosis

-1.72

addons

-1.65

/)

-1.64

olia

-1.62

abuse

-1.55

ARB

-1.54

IPM

-1.54

Rog

-1.54

POSITIVE LOGITS

itely

1.50

wikipedia

1.48

 Explosive

1.47

 skill

1.46

 computed

1.45

ifully

1.45

loo

1.43

Ku

1.42

fter

1.41

 Medals

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.