INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

1:0.09

2:0.09

3:0.08

4:0.06

5:0.08

6:0.07

7:0.07

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

 Genius

-2.92

Ree

-2.82

Ng

-2.80

Neo

-2.74

 Titanium

-2.66

 fingerprint

-2.60

vertisement

-2.59

ocene

-2.58

DNA

-2.54

onian

-2.53

POSITIVE LOGITS

 staffing

2.80

oldown

2.75

 schedules

2.70

whel

2.65

venue

2.61

 budget

2.60

ousand

2.54

dule

2.53

Staff

2.52

 expenditures

2.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.