INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

2:0.08

3:0.07

4:0.09

5:0.09

6:0.09

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 comr

-2.40

wealth

-2.32

anamo

-2.21

NFC

-2.09

illian

-2.08

 dividends

-2.06

 reimbursement

-2.03

 privileges

-2.02

 leverage

-2.02

venge

-2.01

POSITIVE LOGITS

sbm

2.33

ateurs

2.29

Newsletter

2.17

soon

2.11

 Thought

2.10

 Everyday

2.06

casters

2.02

 Called

2.02

tho

2.02

itud

1.98

Activations Density 0.000%

No Known Activations

This feature has no known activations.