INDEX

Explanations

No Explanations Found

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.05

2:0.08

3:0.09

4:0.09

5:0.08

6:0.08

7:0.10

8:0.07

9:0.06

10:0.09

11:0.08

Negative Logits

 weap

-1.77

 autonomy

-1.72

ADRA

-1.64

 Aires

-1.57

MpServer

-1.49

onom

-1.44

Í

-1.43

 advis

-1.43

 heroine

-1.43

Leaks

-1.42

POSITIVE LOGITS

 sink

1.77

 swall

1.75

perse

1.73

 swallow

1.68

 typo

1.65

 Youtube

1.50

 swallowed

1.42

 spit

1.41

 yourselves

1.40

aughs

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.