INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.06

2:0.07

3:0.09

4:0.08

5:0.08

6:0.09

7:0.07

8:0.08

9:0.08

10:0.10

11:0.09

Negative Logits

 PsyNet

-1.52

quit

-1.49

rawdownloadcloneembedreportprint

-1.44

 Rift

-1.41

 Orient

-1.40

 Detected

-1.40

 Response

-1.39

 nausea

-1.38

 aborted

-1.38

 Satanic

-1.35

POSITIVE LOGITS

senal

1.95

ldom

1.91

ourse

1.78

deen

1.71

ourses

1.70

genre

1.67

rency

1.59

ゴン

1.56

ricks

1.54

alach

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.