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

0:0.09

1:0.07

2:0.08

3:0.10

4:0.07

5:0.07

6:0.07

7:0.07

8:0.10

9:0.08

10:0.06

11:0.08

Negative Logits

aples

-1.93

notations

-1.75

Downloadha

-1.73

dain

-1.65

 salads

-1.65

 throats

-1.64

ews

-1.64

 scraps

-1.63

 microw

-1.58

NCT

-1.57

POSITIVE LOGITS

FML

1.74

adian

1.70

EGA

1.58

 Coinbase

1.56

SEA

1.55

 citizen

1.55

orem

1.53

Coh

1.53

nostic

1.52

 publisher

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.