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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.06

2:0.08

3:0.09

4:0.08

5:0.09

6:0.10

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

inar

-1.70

onis

-1.62

inus

-1.57

agus

-1.51

ucker

-1.50

anus

-1.48

rosis

-1.48

aton

-1.47

rix

-1.46

emin

-1.46

POSITIVE LOGITS

 Heist

1.58

enders

1.52

conn

1.51

ONSORED

1.51

jad

1.46

 retaliation

1.42

 retaliate

1.40

quickShipAvailable

1.40

ario

1.37

 fodder

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.