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

1:0.05

2:0.07

3:0.10

4:0.09

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.09

11:0.09

Negative Logits

Muslims

-1.61

 debunked

-1.56

Poll

-1.54

ruciating

-1.53

Safety

-1.53

 classrooms

-1.51

Studies

-1.50

Topics

-1.48

��

-1.48

 Showdown

-1.45

POSITIVE LOGITS

acca

1.80

hai

1.79

assad

1.76

vati

1.74

thia

1.64

SELECT

1.62

zag

1.61

sole

1.59

ulla

1.58

ioch

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.