INDEX

Explanations

martial arts techniques and instructions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.08

1:0.04

2:0.16

3:0.11

4:0.07

5:0.16

6:0.03

7:0.03

8:0.09

9:0.08

10:0.07

11:0.03

Negative Logits

anchester

-1.14

ktop

-1.11

wagen

-1.06

uncture

-1.04

arie

-1.03

atu

-1.01

 Wick

-1.01

hement

-1.00

 Gors

-0.99

emetery

-0.99

POSITIVE LOGITS

-+

1.52

 alike

1.28

yahoo

1.14

acters

1.13

 combo

1.09

Skill

1.06

 combinations

1.01

 combos

0.98

Yo

0.94

catentry

0.94

Activations Density 0.023%

martial arts techniques and instructions

No Comments

No Known Activations