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

3:0.08

4:0.08

5:0.07

6:0.08

7:0.10

8:0.07

9:0.09

10:0.08

11:0.09

Negative Logits

 phosphate

-1.84

 dissenting

-1.75

boa

-1.63

 whichever

-1.58

QC

-1.54

 conscientious

-1.50

mic

-1.49

lder

-1.49

 microphone

-1.48

 sterile

-1.47

POSITIVE LOGITS

thora

2.08

��

2.07

Throw

1.94

ebus

1.91

Ability

1.84

romeda

1.84

MpServer

1.83

ゼウス

1.82

ahime

1.79

ゼ

1.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.