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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.09

4:0.08

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

¨

-3.12

神

-2.73

brow

-2.71

 sermon

-2.69

 Arist

-2.67

................

-2.66

[+]

-2.65

NetMessage

-2.64

ā

-2.59

�

-2.56

POSITIVE LOGITS

rb

3.04

 Neville

2.87

elta

2.58

 Minerva

2.56

pmwiki

2.54

NB

2.52

NB

2.51

 Bella

2.51

alion

2.50

 Berk

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.