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

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

 strengths

-1.69

 Cosponsors

-1.68

orsche

-1.50

 Compet

-1.49

 Integrity

-1.48

 merits

-1.47

 petertodd

-1.46

igers

-1.44

 laure

-1.44

 advoc

-1.42

POSITIVE LOGITS

stretched

1.78

 contracting

1.73

emi

1.64

etting

1.61

eming

1.53

 humming

1.51

figure

1.50

larg

1.42

elong

1.42

 swelling

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.