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

4:0.09

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 encyclopedia

-1.61

 specs

-1.60

 Colleges

-1.55

 interfaces

-1.51

 refrigerator

-1.49

 curated

-1.49

 Library

-1.47

KKK

-1.47

srf

-1.46

 carbohyd

-1.44

POSITIVE LOGITS

wings

1.80

pillar

1.79

icans

1.73

rez

1.68

\">

1.67

\)

1.62

Hope

1.61

Thompson

1.53

switch

1.51

ppard

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.