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

0:0.07

1:0.07

2:0.07

3:0.09

4:0.07

5:0.07

6:0.09

7:0.08

8:0.09

9:0.09

10:0.09

11:0.07

Negative Logits

 ellipt

-2.08

 billions

-2.03

cz

-1.97

 trillions

-1.97

 Schne

-1.97

 ********************************

-1.97

 thorn

-1.96

============

-1.94

-1.91

 Hamm

-1.90

POSITIVE LOGITS

river

2.92

Results

2.64

management

2.36

epend

2.34

orthy

2.23

iaries

2.21

Interstitial

2.17

Firstly

2.16

uala

2.14

itu

2.11

Activations Density 0.000%

No Known Activations

This feature has no known activations.