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

0:0.06

1:0.08

2:0.08

3:0.09

4:0.09

5:0.07

6:0.08

7:0.09

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

 monet

-1.93

 banking

-1.79

McL

-1.62

 billing

-1.62

 licensing

-1.57

 corporate

-1.53

IPO

-1.53

 framing

-1.52

 pree

-1.52

gey

-1.52

POSITIVE LOGITS

Excellent

1.94

BuyableInstoreAndOnline

1.90

Constructed

1.82

Guide

1.72

conserv

1.72

Tool

1.69

Perfect

1.68

uffer

1.67

ustomed

1.65

Woman

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.