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

0:0.08

1:0.06

2:0.08

3:0.07

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

iasco

-1.60

 methodology

-1.48

ripp

-1.46

 unman

-1.45

 documenting

-1.45

 regress

-1.44

vow

-1.40

oner

-1.38

 publicly

-1.34

digy

-1.33

POSITIVE LOGITS

 Appropriations

1.91

lycer

1.72

 Roose

1.64

idth

1.60

uble

1.57

adelphia

1.56

 externalToEVAOnly

1.54

govtrack

1.53

zl

1.51

nikov

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.