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

0:0.06

1:0.10

2:0.09

3:0.09

4:0.09

5:0.08

6:0.08

7:0.07

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

taboola

-2.20

 UNHCR

-2.02

VERTISEMENT

-1.73

 accordingly

-1.70

Sources

-1.68

Products

-1.60

 BELOW

-1.53

Desk

-1.53

Policy

-1.52

[_

-1.52

POSITIVE LOGITS

tein

1.62

jab

1.60

aeda

1.60

schild

1.60

lees

1.56

 Hare

1.56

gew

1.54

irgin

1.52

akia

1.50

bush

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.