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

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.09

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

glers

-1.95

ducers

-1.74

ggles

-1.66

 Finder

-1.65

javascript

-1.62

click

-1.56

ozy

-1.54

ilight

-1.53

EFF

-1.53

mite

-1.52

POSITIVE LOGITS

ibrary

1.76

 TRUMP

1.62

 AMERICA

1.60

cellence

1.55

onne

1.48

TN

1.43

Truth

1.43

udeb

1.42

eur

1.40

sama

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.