INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

2:0.07

3:0.07

4:0.08

5:0.09

6:0.08

7:0.08

8:0.07

9:0.08

10:0.09

11:0.07

Negative Logits

Lie

-2.80

 apples

-2.77

 imperative

-2.75

 potato

-2.74

 recl

-2.69

 retrie

-2.66

 hawk

-2.66

 hike

-2.62

 multit

-2.61

 apple

-2.60

POSITIVE LOGITS

etheless

3.24

 Cameroon

2.88

ileged

2.72

 Fiction

2.70

 Writers

2.68

 Marketable

2.65

ivals

2.64

 LGBTQ

2.62

yrights

2.59

 Wizards

2.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.