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

0:0.08

1:0.06

2:0.09

3:0.07

4:0.08

5:0.09

6:0.09

7:0.09

8:0.09

9:0.06

10:0.08

11:0.09

Negative Logits

ascus

-2.32

oshenko

-2.09

sembly

-2.02

apons

-1.92

rape

-1.89

iversary

-1.84

chwitz

-1.81

corruption

-1.81

omics

-1.79

ocalypse

-1.75

POSITIVE LOGITS

que

1.76

ITV

1.62

Pyr

1.60

 Plat

1.57

Vu

1.53

 Spotify

1.50

 contribut

1.47

 Pier

1.45

 Channel

1.44

[_

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.