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

1:0.12

2:0.07

3:0.08

4:0.07

5:0.07

6:0.07

7:0.08

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 Hive

-1.75

 sweat

-1.65

opia

-1.64

 stacks

-1.61

worth

-1.50

 negligence

-1.45

paw

-1.44

iability

-1.41

hare

-1.37

itudinal

-1.37

POSITIVE LOGITS

Forge

1.81

Finish

1.66

agne

1.64

Interstitial

1.63

TIT

1.61

Prot

1.60

dial

1.58

Steam

1.54

Ark

1.54

Opening

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.