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

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

────

-2.78

Wik

-2.76

OPER

-2.69

 Citiz

-2.66

 Correction

-2.58

================

-2.46

chuk

-2.46

scrib

-2.43

 agre

-2.40

Wem

-2.40

POSITIVE LOGITS

 crashes

3.00

 Bloom

2.62

 peaks

2.55

 Katy

2.52

 sidel

2.50

 plateau

2.47

 booming

2.46

 garn

2.38

 speeding

2.36

 Clover

2.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.