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

0:0.07

1:0.07

2:0.09

3:0.10

4:0.07

5:0.08

6:0.07

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

ieval

-2.83

 clot

-2.77

leck

-2.75

 reconcil

-2.60

 spare

-2.59

 underwear

-2.56

 reconcile

-2.53

unks

-2.48

 semin

-2.45

athed

-2.40

POSITIVE LOGITS

JM

2.91

 ACTIONS

2.81

MU

2.56

 Telesc

2.43

 Jupiter

2.42

:[

2.42

Russ

2.42

Jaw

2.40

=-=-=-=-

2.38

Tul

2.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.