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

1:0.05

2:0.08

3:0.09

4:0.08

5:0.07

6:0.08

7:0.09

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

 Sussex

-1.69

 departures

-1.65

kefeller

-1.63

umenthal

-1.59

interstitial

-1.52

 Suffolk

-1.51

urrence

-1.49

 Mellon

-1.48

anyon

-1.48

NTS

-1.47

POSITIVE LOGITS

?).

1.79

ovember

1.77

 Therapy

1.46

?),

1.44

 Alone

1.44

 Recall

1.42

!).

1.42

gel

1.42

ゴン

1.40

 Simulator

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.