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

1:0.07

2:0.07

3:0.09

4:0.09

5:0.09

6:0.08

7:0.08

8:0.07

9:0.06

10:0.08

11:0.08

Negative Logits

 cues

-1.61

Shape

-1.57

Fro

-1.53

grad

-1.48

gl

-1.41

 outp

-1.40

boards

-1.40

 Shap

-1.38

 hypoc

-1.38

Xi

-1.35

POSITIVE LOGITS

ussion

1.73

ogi

1.69

�

1.60

advertising

1.59

ogie

1.54

版

1.52

 Advertisement

1.52

 Flavoring

1.52

ドラゴン

1.49

malink

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.