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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 rapport

-2.79

Gap

-2.19

 clauses

-2.06

 ministries

-2.06

 credits

-2.00

 Scher

-2.00

 portfolios

-1.99

 Clause

-1.99

 Cohn

-1.98

 briefings

-1.97

POSITIVE LOGITS

Downloadha

2.57

regon

2.09

cause

2.09

lycer

2.09

��

2.08

 unbel

2.08

 ---------

2.02

 combust

2.01

elaide

2.01

ourge

2.00

Activations Density 0.000%

No Known Activations

This feature has no known activations.