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

0:0.07

1:0.08

2:0.08

3:0.09

4:0.09

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

yrights

-1.74

Collection

-1.67

 Estate

-1.66

Dir

-1.65

 perjury

-1.55

 Veil

-1.55

 Schne

-1.50

Hau

-1.45

 Alzheimer

-1.45

░

-1.44

POSITIVE LOGITS

uncture

1.73

yout

1.61

undai

1.55

 vividly

1.54

htaking

1.52

edin

1.47

 reminds

1.44

xtap

1.43

ounced

1.43

gently

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.