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

0:0.09

1:0.06

2:0.08

3:0.08

4:0.07

5:0.08

6:0.08

7:0.07

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

mud

-1.93

Jews

-1.88

thodox

-1.86

tery

-1.85

joice

-1.81

cling

-1.80

gage

-1.74

lasses

-1.72

upuncture

-1.72

ieties

-1.71

POSITIVE LOGITS

SOS

1.78

 immedi

1.73

 Inform

1.62

 Crash

1.61

 Zeit

1.58

IB

1.57

ainment

1.54

 roadmap

1.54

 Interactive

1.53

 wildfire

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.