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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.07

3:0.08

4:0.09

5:0.08

6:0.07

7:0.10

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

uncture

-1.75

Nex

-1.57

nces

-1.56

iencies

-1.51

eteenth

-1.49

qus

-1.48

zig

-1.45

abase

-1.45

 Unle

-1.45

 carbohyd

-1.43

POSITIVE LOGITS

 knitting

1.56

hatt

1.47

 brick

1.47

 gesture

1.46

DJs

1.44

 spirits

1.43

 Lithuan

1.39

 tradition

1.39

 conserv

1.38

 committees

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.