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

1:0.06

2:0.08

3:0.09

4:0.09

5:0.07

6:0.09

7:0.08

8:0.07

9:0.09

10:0.09

11:0.07

Negative Logits

 outcomes

-2.93

…]

-2.80

 […]

-2.75

...]

-2.65

 [...]

-2.62

 breaches

-2.61

‎

-2.52

 whistleblowers

-2.43

 headline

-2.40

 cannabinoids

-2.39

POSITIVE LOGITS

TOD

3.14

ETF

2.82

HUD

2.77

obin

2.66

gor

2.65

龍喚士

2.65

 Franch

2.60

ammy

2.58

�

2.58

zeb

2.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.