INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.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

0:0.10

1:0.09

2:0.10

3:0.07

4:0.07

5:0.08

6:0.05

7:0.06

8:0.08

9:0.10

10:0.09

11:0.06

Negative Logits

 repr

-1.64

 whistle

-1.50

 weighing

-1.49

 nozzle

-1.48

 monop

-1.48

medium

-1.47

pus

-1.45

vol

-1.45

 cellul

-1.45

 Tess

-1.41

POSITIVE LOGITS

icans

2.14

gaard

1.94

gey

1.82

ahime

1.82

â

1.80

iji

1.78

arij

1.75

abin

1.72

�

1.68

ALLY

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.