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

0:0.07

1:0.09

2:0.09

3:0.08

4:0.06

5:0.10

6:0.08

7:0.06

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

Story

-1.66

letters

-1.64

=(

-1.61

Mask

-1.59

=>

-1.58

 Shields

-1.51

NECT

-1.50

Face

-1.48

.;

-1.46

 Letters

-1.45

POSITIVE LOGITS

mble

2.24

 tremend

2.05

staking

1.93

ixtape

1.86

ensual

1.83

milo

1.82

 challeng

1.68

ategory

1.68

lished

1.62

retty

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.