INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

1:0.07

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

 Specifications

-2.83

 CLSID

-2.79

 undisclosed

-2.72

ogun

-2.70

GC

-2.65

istration

-2.58

 Annotations

-2.58

 Publication

-2.56

 redacted

-2.52

 Bounty

-2.52

POSITIVE LOGITS

psy

2.64

�

2.60

los

2.58

stre

2.57

Stre

2.56

ultural

2.41

 cheering

2.36

 hust

2.35

phe

2.29

rid

2.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.