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

0:0.10

1:0.07

2:0.09

3:0.09

4:0.09

5:0.07

6:0.07

7:0.07

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

 Shel

-1.92

 ally

-1.80

 Thib

-1.78

Alz

-1.75

 Allies

-1.73

Gry

-1.65

 Remy

-1.64

 UNHCR

-1.59

 MSNBC

-1.59

 Fischer

-1.56

POSITIVE LOGITS

eeper

2.04

ecycle

1.92

�

1.91

ventures

1.90

venants

1.83

iage

1.76

idency

1.76

ertodd

1.75

Hash

1.75

IGHTS

1.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.