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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

baugh

-1.84

PLA

-1.74

=>

-1.67

®

-1.64

 Advertisement

-1.64

vals

-1.63

>>

-1.63

 holders

-1.62

AE

-1.60

ga

-1.60

POSITIVE LOGITS

 instincts

2.12

atche

2.05

etheless

2.03

使

1.95

exper

1.74

 adaptations

1.72

 enthus

1.67

��

1.66

mosp

1.65

opian

1.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.