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

3:0.09

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

velength

-1.95

 premie

-1.76

naissance

-1.72

please

-1.67

unes

-1.63

-1.62

Legend

-1.57

film

-1.56

odynamics

-1.54

 premiere

-1.52

POSITIVE LOGITS

mons

1.80

ween

1.77

aughed

1.62

emet

1.58

uese

1.56

ribut

1.56

ware

1.53

okemon

1.52

Compat

1.52

irgin

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.