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

1:0.05

2:0.08

3:0.08

4:0.10

5:0.10

6:0.08

7:0.06

8:0.09

9:0.07

10:0.07

11:0.09

Negative Logits

awan

-1.62

 inertia

-1.54

_-

-1.53

 Drift

-1.43

POL

-1.40

 optimism

-1.39

 reflection

-1.39

 drift

-1.39

 curiosity

-1.38

 restraint

-1.38

POSITIVE LOGITS

RFC

1.74

osponsors

1.71

Downloadha

1.71

aturday

1.70

MMR

1.68

yll

1.68

の魔

1.67

natureconservancy

1.65

imei

1.62

MpServer

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.