INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.07

2:0.10

3:0.07

4:0.09

5:0.06

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

ERC

-2.93

 GOODMAN

-2.79

 Byrd

-2.77

yg

-2.71

library

-2.68

 Hubble

-2.63

WB

-2.60

 Kard

-2.57

WCS

-2.56

 Cosponsors

-2.56

POSITIVE LOGITS

umbai

3.21

irements

2.91

achelor

2.58

 Sasuke

2.57

 visa

2.56

vin

2.56

 avail

2.48

 induct

2.43

 Hassan

2.40

 pane

2.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.