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

0:0.09

1:0.06

2:0.09

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.09

10:0.07

11:0.08

Negative Logits

govtrack

-1.87

apon

-1.86

inous

-1.76

ailability

-1.73

iuses

-1.69

 sparing

-1.62

inances

-1.60

 Exhibition

-1.60

senal

-1.55

vernment

-1.53

POSITIVE LOGITS

GROUP

1.79

________________________________________________________________

1.77

Synopsis

1.60

 Rasmussen

1.58

realDonaldTrump

1.56

AIN

1.52

 separation

1.51

beck

1.49

tera

1.49

LET

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.