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

0:0.08

1:0.04

2:0.10

3:0.09

4:0.10

5:0.08

6:0.09

7:0.07

8:0.07

9:0.06

10:0.08

11:0.08

Negative Logits

aples

-2.16

anwhile

-1.94

undown

-1.90

aturday

-1.86

 Goods

-1.85

ovember

-1.81

arta

-1.80

aband

-1.77

uria

-1.75

artifacts

-1.69

POSITIVE LOGITS

 persona

1.51

Brit

1.48

 opposite

1.46

 fart

1.45

 faire

1.44

 bloom

1.43

 ideal

1.43

 adapt

1.42

 anim

1.38

 devoted

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.