INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

1:0.09

2:0.09

3:0.10

4:0.08

5:0.06

6:0.06

7:0.10

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 poker

-2.08

 feather

-1.98

 volleyball

-1.96

ザ

-1.95

interstitial

-1.83

��

-1.83

DF

-1.77

 auction

-1.74

 delta

-1.72

\"

-1.69

POSITIVE LOGITS

ufact

2.90

conom

2.31

ivil

2.18

imity

2.16

SPONSORED

2.14

morrow

2.06

culture

2.02

 Invention

1.98

IPM

1.95

 ASAP

1.93

Activations Density 0.000%

No Known Activations

This feature has no known activations.