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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

ngth

-3.54

shit

-3.08

Ty

-2.98

Gon

-2.88

 Shit

-2.67

imp

-2.64

TC

-2.61

fuck

-2.60

Stre

-2.60

�

-2.55

POSITIVE LOGITS

..."

2.71

 Atlantis

2.61

`.

2.53

itage

2.50

oire

2.49

 Answer

2.42

��

2.41

alus

2.37

nexus

2.35

onite

2.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.