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

2:0.06

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.09

9:0.08

10:0.09

11:0.09

Negative Logits

icago

-2.00

ivot

-1.78

 Porter

-1.74

pherd

-1.64

eger

-1.63

Pie

-1.59

elo

-1.58

zer

-1.56

oğan

-1.55

 DRAG

-1.54

POSITIVE LOGITS

TPPStreamerBot

1.57

 credential

1.54

 fitt

1.54

TeX

1.52

emale

1.51

DN

1.51

workshop

1.49

 Armory

1.48

 cele

1.46

 fingerprint

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.