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

1:0.08

2:0.08

3:0.08

4:0.09

5:0.07

6:0.09

7:0.08

8:0.06

9:0.09

10:0.08

11:0.08

Negative Logits

ividual

-1.79

levant

-1.71

Marginal

-1.67

etc

-1.59

 Posted

-1.56

inki

-1.52

abiding

-1.52

aneers

-1.50

 Flavoring

-1.50

POSITIVE LOGITS

FU

1.87

1.65

Gh

1.63

ilk

1.57

oos

1.45

mk

1.44

GR

1.43

 Braz

1.41

Gan

1.41

 congratulations

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.