INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

1:0.08

2:0.08

3:0.07

4:0.08

5:0.07

6:0.08

7:0.08

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

 Gazette

-2.34

 edited

-2.08

rafted

-2.06

Newsletter

-2.04

(@

-2.04

 Saunders

-2.03

anian

-1.92

study

-1.90

 Caucus

-1.89

Mich

-1.87

POSITIVE LOGITS

appiness

2.38

VALUE

2.29

otonin

2.12

 裏覚醒

2.11

priority

2.11

ocom

2.08

 Yards

1.99

 congestion

1.98

 commuters

1.92

obar

1.89

Activations Density 0.000%

No Known Activations

This feature has no known activations.