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

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.08

4:0.07

5:0.09

6:0.07

7:0.09

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

milo

-3.33

paio

-3.04

anka

-3.00

ocre

-2.92

assium

-2.87

kson

-2.71

��

-2.68

byter

-2.65

Wisconsin

-2.62

ascus

-2.61

POSITIVE LOGITS

 Cargo

2.90

 tether

2.85

 cataly

2.76

 Vessel

2.72

 Collective

2.63

 humanitarian

2.56

 vital

2.51

ベ

2.44

 relational

2.40

 Underground

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.