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

1:0.10

2:0.08

3:0.07

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

osphere

-1.94

Spa

-1.71

Frameworks

-1.70

cs

-1.68

 Latvia

-1.68

Tes

-1.66

 Colleges

-1.59

�

-1.57

Depths

-1.56

Nou

-1.55

POSITIVE LOGITS

 smugg

1.82

plet

1.79

 smugglers

1.73

odge

1.71

 advis

1.65

oğ

1.62

achus

1.61

[+]

1.61

 authenticated

1.58

iscal

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.