INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.08

2:0.08

3:0.07

4:0.08

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

RES

-2.97

 repe

-2.71

ledge

-2.71

THER

-2.70

ウス

-2.68

weather

-2.56

ennis

-2.54

hower

-2.53

 Ellis

-2.52

activ

-2.46

POSITIVE LOGITS

ibaba

3.02

itate

2.87

 warehouse

2.78

 Copy

2.77

 warehouses

2.68

 renting

2.61

 pharmacy

2.58

 pubs

2.57

Export

2.57

 Nanto

2.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.