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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.09

2:0.09

3:0.08

4:0.07

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.07

11:0.07

Negative Logits

jriwal

-2.47

rud

-2.15

�

-2.09

 gravy

-2.08

Rud

-2.07

 Babel

-2.06

-----------

-2.01

 greedy

-1.99

AAA

-1.98

Tit

-1.96

POSITIVE LOGITS

utical

2.43

affiliated

2.31

 refurb

2.27

 Clinic

2.18

apeshifter

2.16

 Exile

2.13

 researching

2.12

 risked

2.06

 afterlife

2.03

 resear

2.01

Activations Density 0.000%

No Known Activations

This feature has no known activations.