INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.07

5:0.08

6:0.06

7:0.07

8:0.09

9:0.07

10:0.10

11:0.08

Negative Logits

oyd

-3.15

Exit

-3.04

Rand

-2.91

overe

-2.87

Strike

-2.80

rawler

-2.80

ossus

-2.71

 Lone

-2.69

Known

-2.65

collect

-2.65

POSITIVE LOGITS

 Alger

2.78

 Ministry

2.75

 counselling

2.70

 Psychology

2.69

 partName

2.67

�

2.66

 Algeria

2.62

 Buddh

2.61

 anesthesia

2.56

 Helsinki

2.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.