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

2:0.08

3:0.08

4:0.10

5:0.07

6:0.07

7:0.07

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

eatures

-1.98

OIL

-1.81

ortmund

-1.76

 graphs

-1.65

arten

-1.64

akings

-1.62

 SOFTWARE

-1.59

oil

-1.58

soDeliveryDate

-1.56

 UPDATE

-1.55

POSITIVE LOGITS

ener

1.78

Friend

1.67

 parap

1.57

ْ

1.56

 lighter

1.55

 Sleeping

1.55

Scot

1.54

ibrary

1.54

 decl

1.52

mental

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.