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

1:0.07

2:0.09

3:0.07

4:0.08

5:0.07

6:0.07

7:0.08

8:0.09

9:0.09

10:0.07

11:0.08

Negative Logits

 actionGroup

-2.96

-2.79

-2.77

 adolesc

-2.72

-2.68

-2.63

��

-2.60

-2.59

-2.58

 Lifetime

-2.55

POSITIVE LOGITS

 Kraken

3.10

 Prediction

2.81

uggest

2.77

 Chimera

2.77

conservancy

2.66

 Klopp

2.62

etsk

2.57

 Nept

2.54

 Chocobo

2.52

MpServer

2.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.