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

0:0.07

1:0.07

2:0.09

3:0.09

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 remembering

-1.60

 anew

-1.55

 ourselves

-1.53

 Communities

-1.53

 affirmation

-1.52

 renewed

-1.50

 passage

-1.42

 recess

-1.42

 Mexicans

-1.40

 individual

-1.39

POSITIVE LOGITS

inventoryQuantity

2.23

yip

2.12

quickShipAvailable

2.10

ーク

1.93

elta

1.92

hots

1.79

[+

1.72

park

1.72

mil

1.72

romeda

1.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.