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

1:0.06

2:0.09

3:0.10

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

tf

-1.66

ventions

-1.64

views

-1.64

 thesis

-1.63

 Plans

-1.63

tml

-1.58

disciplinary

-1.58

���

-1.57

thood

-1.56

conserv

-1.55

POSITIVE LOGITS

oother

1.89

 stranger

1.81

MSN

1.66

skip

1.62

fou

1.55

ocobo

1.55

idium

1.52

 Fenrir

1.50

 Sawyer

1.50

byss

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.