INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

1:0.09

2:0.09

3:0.07

4:0.07

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

}}

-2.90

ittees

-2.76

OGR

-2.63

hai

-2.60

orgetown

-2.58

urtles

-2.54

okin

-2.52

 marines

-2.52

 fins

-2.51

ective

-2.49

POSITIVE LOGITS

 Verb

2.96

 Fair

2.90

Bib

2.77

 Breakfast

2.60

 hourly

2.58

cham

2.50

fair

2.48

 Barn

2.47

 commute

2.46

 Cumber

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.