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

0:0.09

1:0.08

2:0.09

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.09

9:0.06

10:0.08

11:0.07

Negative Logits

mentioned

-1.65

ean

-1.54

\":

-1.51

 Horizon

-1.45

Spoiler

-1.36

Thor

-1.36

 Mirage

-1.32

 explanatory

-1.32

 Carbuncle

-1.31

 vein

-1.31

POSITIVE LOGITS

��

1.85

lethal

1.82

iage

1.77

anners

1.72

 deeds

1.64

zin

1.61

 deed

1.61

cules

1.60

senal

1.58

HAEL

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.