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

1:0.07

2:0.07

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

shock

-1.59

 Hurt

-1.58

 sponsors

-1.51

buster

-1.46

 Shade

-1.44

rgb

-1.43

SPONSORED

-1.43

osphere

-1.42

sil

-1.39

Sab

-1.39

POSITIVE LOGITS

tein

2.02

 sqor

1.99

 Parables

1.94

ichever

1.84

theless

1.69

 utmost

1.62

vow

1.62

*/(

1.60

ouk

1.58

ongyang

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.