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

0:0.10

1:0.08

2:0.08

3:0.09

4:0.08

5:0.09

6:0.08

7:0.06

8:0.09

9:0.07

10:0.06

11:0.06

Negative Logits

 Entered

-1.99

ascript

-1.72

 Received

-1.66

 Reincarn

-1.64

 Form

-1.60

perties

-1.60

 Cross

-1.56

Qin

-1.56

anism

-1.55

aware

-1.55

POSITIVE LOGITS

YE

1.83

amy

1.78

ESA

1.59

ophon

1.57

 hats

1.50

 golden

1.45

 boom

1.44

toggle

1.43

 almond

1.43

 ringing

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.