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

0:0.07

1:0.08

2:0.07

3:0.09

4:0.09

5:0.08

6:0.06

7:0.09

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

endas

-3.40

inho

-3.03

aucuses

-2.92

 veto

-2.90

ishops

-2.87

eto

-2.85

mun

-2.80

Pope

-2.75

ushima

-2.74

adra

-2.73

POSITIVE LOGITS

ABE

3.68

RL

2.88

MM

2.85

 Stevenson

2.80

LI

2.79

QC

2.76

JR

2.66

TN

2.62

ALE

2.62

WD

2.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.