INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

0:0.06

1:0.10

2:0.09

3:0.09

4:0.10

5:0.08

6:0.08

7:0.07

8:0.07

9:0.05

10:0.08

11:0.08

Negative Logits

 confinement

-1.16

 Mutant

-1.14

,[

-1.12

 synthesis

-1.12

[&

-1.11

 Mandal

-1.09

 Fiat

-1.07

 -------

-1.04

-1.03

 Veronica

-1.01

POSITIVE LOGITS

laus

1.29

christ

1.23

aith

1.19

)))

1.16

estone

1.16

orah

1.15

Tier

1.14

_-

1.13

ses

1.11

call

1.11

Activations Density 0.000%

No Known Activations

This feature has no known activations.