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

0:0.07

1:0.06

2:0.08

3:0.09

4:0.09

5:0.08

6:0.09

7:0.08

8:0.07

9:0.08

10:0.09

11:0.07

Negative Logits

 Journalists

-1.69

Journal

-1.65

 Stats

-1.51

 Newspaper

-1.46

itely

-1.45

 Cheong

-1.44

arth

-1.43

 journalists

-1.42

 Heller

-1.40

cients

-1.39

POSITIVE LOGITS

 prest

1.66

\<

1.62

 footing

1.60

dylib

1.56

 fares

1.55

steen

1.53

ffen

1.53

 upkeep

1.51

LSD

1.51

ABV

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.