INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

1:0.09

2:0.08

3:0.08

4:0.07

5:0.07

6:0.07

7:0.09

8:0.07

9:0.08

10:0.07

11:0.09

Negative Logits

��

-2.23

forcement

-2.11

fitting

-2.04

lined

-2.03

eling

-2.02

erial

-1.98

ín

-1.96

 Bale

-1.94

ulnerable

-1.92

ilar

-1.92

POSITIVE LOGITS

 scient

2.45

 volunt

2.32

 advoc

2.30

 proced

2.30

morrow

2.25

 enthus

2.24

 enthusi

2.17

 presupp

2.17

 deliberations

2.17

 tomorrow

2.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.