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

1:0.06

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.09

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

appropriately

-1.62

osate

-1.61

undai

-1.59

 illegally

-1.55

ajo

-1.54

una

-1.51

argo

-1.50

ikarp

-1.48

 adversely

-1.47

exempt

-1.46

POSITIVE LOGITS

 Characters

1.74

光

1.74

 srfAttach

1.70

 Example

1.64

 Parables

1.64

 curves

1.57

 Printed

1.54

 detail

1.53

 Plain

1.51

oried

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.