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

1:0.07

2:0.08

3:0.09

4:0.08

5:0.07

6:0.08

7:0.08

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

]}

-1.68

Hew

-1.61

RTX

-1.61

 intervening

-1.56

MH

-1.56

 Galile

-1.53

GH

-1.51

 Investigations

-1.50

HIV

-1.50

 Inqu

-1.48

POSITIVE LOGITS

1.69

 turnover

1.65

�

1.64

FIELD

1.63

erous

1.62

ワ

1.61

 newcom

1.60

umber

1.59

soDeliveryDate

1.58

 manag

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.