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

0:0.08

1:0.07

2:0.09

3:0.08

4:0.06

5:0.08

6:0.08

7:0.07

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

 Fiat

-1.69

amping

-1.59

TPS

-1.59

 裏�

-1.57

 Kamp

-1.52

ICES

-1.48

acked

-1.46

Accept

-1.46

 convertible

-1.46

UID

-1.44

POSITIVE LOGITS

soDeliveryDate

2.29

idae

1.77

andre

1.77

 pige

1.76

heid

1.75

sic

1.75

yrus

1.71

Spoiler

1.70

 Leilan

1.68

)))

1.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.