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

0:0.10

1:0.07

2:0.08

3:0.07

4:0.06

5:0.10

6:0.08

7:0.07

8:0.09

9:0.08

10:0.07

11:0.08

Negative Logits

geries

-1.90

velength

-1.69

ministic

-1.65

orage

-1.64

SPONSORED

-1.63

essage

-1.52

scribe

-1.46

gery

-1.45

 rendition

-1.45

 curated

-1.44

POSITIVE LOGITS

erella

1.71

Pwr

1.65

lust

1.59

midt

1.54

peed

1.52

horn

1.51

amus

1.50

plet

1.47

amac

1.47

 legs

1.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.