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

1:0.07

2:0.06

3:0.08

4:0.08

5:0.07

6:0.09

7:0.09

8:0.08

9:0.08

10:0.10

11:0.08

Negative Logits

 Sparks

-1.75

Nug

-1.66

 brilliance

-1.61

 spark

-1.59

 disl

-1.51

 jealousy

-1.51

 chuck

-1.50

 shook

-1.50

 Puzz

-1.50

�

-1.49

POSITIVE LOGITS

mare

2.19

artments

2.02

meal

2.00

vernment

2.00

byter

1.98

veland

1.94

angel

1.94

achine

1.91

alone

1.85

iliary

1.83

Activations Density 0.000%

No Known Activations

This feature has no known activations.