INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

2:0.07

3:0.08

4:0.09

5:0.06

6:0.06

7:0.08

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

��

-2.71

λ

-2.60

 grav

-2.55

hov

-2.49

 electr

-2.47

iesel

-2.47

τ

-2.47

�

-2.44

 compr

-2.42

hner

-2.42

POSITIVE LOGITS

 Anaheim

3.10

PST

2.85

PDT

2.77

 Scot

2.76

 Sierra

2.69

 Bean

2.66

SAS

2.66

 Acer

2.57

 captcha

2.57

 Douglas

2.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.