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

0:0.09

1:0.05

2:0.09

3:0.08

4:0.08

5:0.09

6:0.06

7:0.08

8:0.07

9:0.08

10:0.10

11:0.07

Negative Logits

achelor

-1.66

Vs

-1.63

anship

-1.60

aphael

-1.57

ynthesis

-1.54

orescence

-1.50

phia

-1.49

urgy

-1.46

inks

-1.46

acebook

-1.46

POSITIVE LOGITS

forced

1.48

 WARN

1.45

 encour

1.45

 excuse

1.44

severe

1.42

 leptin

1.40

 issuer

1.35

force

1.34

 disclaimer

1.34

 forcing

1.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.