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

1:0.08

2:0.09

3:0.08

4:0.07

5:0.07

6:0.08

7:0.10

8:0.07

9:0.06

10:0.08

11:0.08

Negative Logits

 Cosponsors

-1.89

 Jinn

-1.77

||

-1.73

 Skywalker

-1.72

QC

-1.67

 Nielsen

-1.64

 Immunity

-1.64

$$$$

-1.63

 Schumer

-1.63

 Superman

-1.63

POSITIVE LOGITS

aughters

2.03

ongyang

1.90

orthy

1.80

sterdam

1.78

iffe

1.74

erva

1.71

iaries

1.69

lict

1.68

itiz

1.68

 Franch

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.