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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.07

3:0.07

4:0.08

5:0.09

6:0.08

7:0.09

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

tymology

-1.93

ocry

-1.77

ipment

-1.73

Downloadha

-1.72

 carbohyd

-1.62

 accur

-1.61

origin

-1.60

 clipboard

-1.58

chnology

-1.57

 reused

-1.55

POSITIVE LOGITS

 Warner

1.75

 Romeo

1.65

 Forbes

1.62

 Garland

1.49

payer

1.49

 Garrison

1.49

 Gonz

1.49

 wealthiest

1.48

 Ross

1.48

 Norton

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.