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

2:0.07

3:0.07

4:0.08

5:0.07

6:0.09

7:0.09

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

gb

-3.14

ortmund

-2.82

jong

-2.81

jobs

-2.67

ploma

-2.59

emouth

-2.58

SpaceEngineers

-2.56

orf

-2.43

 Peng

-2.40

club

-2.36

POSITIVE LOGITS

thia

2.50

··

2.49

 hostage

2.47

zsche

2.36

mire

2.33

 STOR

2.33

 …"

2.33

 Persian

2.32

 recy

2.32

que

2.32

Activations Density 0.000%

No Known Activations

This feature has no known activations.