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

1:0.08

2:0.06

3:0.09

4:0.05

5:0.07

6:0.07

7:0.10

8:0.05

9:0.12

10:0.07

11:0.11

Negative Logits

displayText

-2.66

�

-2.64

erva

-2.56

ioxid

-2.55

igue

-2.52

udeb

-2.52

Import

-2.51

asury

-2.48

iso

-2.40

ァ

-2.35

POSITIVE LOGITS

 disappears

2.19

 vanished

2.18

 doll

2.11

 broch

2.10

 tattoo

2.10

 styl

2.03

 somewhere

2.02

 billboard

1.97

 disappeared

1.96

 squat

1.94

Activations Density 0.000%

No Known Activations

This feature has no known activations.